diff --git a/.gitignore b/.gitignore index fa18ca83c3..ceafeb756e 100644 --- a/.gitignore +++ b/.gitignore @@ -36,3 +36,4 @@ node_modules .DS_Store *.fst *.arpa +.venv/ diff --git a/egs/vctk/TTS/README.md b/egs/vctk/TTS/README.md index c2703dbe2c..9e026d7f1a 100644 --- a/egs/vctk/TTS/README.md +++ b/egs/vctk/TTS/README.md @@ -1,10 +1,36 @@ # Introduction -This CSTR VCTK Corpus includes speech data uttered by 110 English speakers with various accents. Each speaker reads out about 400 sentences, which were selected from a newspaper, the rainbow passage and an elicitation paragraph used for the speech accent archive. -The newspaper texts were taken from Herald Glasgow, with permission from Herald & Times Group. Each speaker has a different set of the newspaper texts selected based a greedy algorithm that increases the contextual and phonetic coverage. -The details of the text selection algorithms are described in the following paper: [C. Veaux, J. Yamagishi and S. King, "The voice bank corpus: Design, collection and data analysis of a large regional accent speech database,"](https://doi.org/10.1109/ICSDA.2013.6709856). +Key features of VITS: -The above information is from the [CSTR VCTK website](https://datashare.ed.ac.uk/handle/10283/3443). +Combines VAE (Variational Autoencoder), normalizing flow, and GAN (adversarial training with a discriminator). +Uses Monotonic Alignment Search (MAS) — the model learns the alignment between text and audio automatically (no need for separate forced alignment like in older models). +Supports multi-speaker training (VCTK has ~109 different English speakers). +Generates natural-sounding speech with good prosody and voice quality. + +The notebook uses the icefall implementation of VITS (generator + discriminator). + +![alt text](image.png) + +# Data Preparation + +Run `prepare.sh` to download and prepare the data. All stages are run by default. + +**Option A — Download automatically (default):** +```bash +bash prepare.sh +``` + +**Option B — Use pre-existing local data (skip download):** + +If you already have the VCTK corpus available locally (e.g. from [Kaggle](https://www.kaggle.com/datasets/pratt3000/vctk-corpus) +or another source), pass `--local-data-dir` to skip Stage 0 download: + +```bash +bash prepare.sh --local-data-dir /path/to/your/VCTK +``` + +This will create a symlink at `download/VCTK` pointing to your local copy, +so all subsequent stages work without any modification. # VITS @@ -22,7 +48,7 @@ export CUDA_VISIBLE_DEVICES="0,1,2,3" --num-epochs 1000 \ --start-epoch 1 \ --exp-dir vits/exp \ - --tokens data/tokens.txt + --tokens data/tokens.txt \ --max-duration 350 ``` diff --git a/egs/vctk/TTS/image.png b/egs/vctk/TTS/image.png new file mode 100644 index 0000000000..84fe89f272 Binary files /dev/null and b/egs/vctk/TTS/image.png differ diff --git a/egs/vctk/TTS/infer_pretrained.md b/egs/vctk/TTS/infer_pretrained.md new file mode 100644 index 0000000000..a38111fcf3 --- /dev/null +++ b/egs/vctk/TTS/infer_pretrained.md @@ -0,0 +1,84 @@ +# Inference with Pretrained VITS Model + +### Cell 1: Install Dependencies +```bash +# Install icefall repo and requirements +!git clone https://github.com/k2-fsa/icefall.git /kaggle/working/icefall +!pip install -r /kaggle/working/icefall/requirements.txt +!grep -v 'numba' /kaggle/working/icefall/requirements-tts.txt | pip install -r /dev/stdin +!pip install "numba>=0.59.0" + +# Install lhotse (audio dataset toolkit) +!pip install lhotse + +# Install k2 (must match CUDA 12.8 + PyTorch 2.10.0) +!pip install k2==1.24.4.dev20260306+cuda12.8.torch2.10.0 -f https://k2-fsa.github.io/k2/cuda.html + +# Install piper_phonemize and register icefall +!pip install piper_phonemize -f https://k2-fsa.github.io/icefall/piper_phonemize.html +!pip install -e /kaggle/working/icefall +``` + +### Cell 2: Prepare Dataset +```bash +%cd /kaggle/working/icefall/egs/vctk/TTS + +# Symlink VCTK data to bypass download stage +!mkdir -p download +!ln -sfv /kaggle/input/datasets/ download/VCTK + +# Build monotonic_align C extension +!bash prepare.sh --stage -1 --stop_stage -1 + +# Create manifests, spectrograms, tokens, and data splits +!bash prepare.sh --stage 1 --stop_stage 4 +``` + +### Cell 3: Download Pretrained Model +```python +from huggingface_hub import hf_hub_download +import os, shutil + +MODEL_ID = "zrjin/icefall-tts-vctk-vits-2024-03-18" +BASE_DIR = "/kaggle/working/icefall/egs/vctk/TTS" + +os.makedirs(f"{BASE_DIR}/vits/exp", exist_ok=True) +os.makedirs(f"{BASE_DIR}/data", exist_ok=True) + +# Download checkpoint and move to correct directory +hf_hub_download(repo_id=MODEL_ID, filename="exp/epoch-1000.pt", local_dir=BASE_DIR) +shutil.copy2(f"{BASE_DIR}/exp/epoch-1000.pt", f"{BASE_DIR}/vits/exp/epoch-1000.pt") + +# Download tokens and speakers +hf_hub_download(repo_id=MODEL_ID, filename="data/tokens.txt", local_dir=BASE_DIR) +hf_hub_download(repo_id=MODEL_ID, filename="data/speakers.txt", local_dir=BASE_DIR) + +print("Pretrained model downloaded and moved to correct directories.") +``` + +### Cell 4: Run Inference +```bash +%cd /kaggle/working/icefall/egs/vctk/TTS + +!CUDA_VISIBLE_DEVICES="0" python vits/infer.py \ + --epoch 1000 \ + --exp-dir vits/exp \ + --tokens data/tokens.txt \ + --max-duration 500 +``` + +### Cell 5: Play Generated Audio +```python +import os +from IPython.display import Audio, display + +wav_dir = "/kaggle/working/icefall/egs/vctk/TTS/vits/exp/infer/epoch-1000/wav" +# Choose to play audio from test set directory +wav_dir_test = os.path.join(wav_dir, "test") +wav_files = sorted(os.listdir(wav_dir_test)) + +# Play the first 3 generated audio files +for f in wav_files[:3]: + print(f) + display(Audio(os.path.join(wav_dir_test, f))) +``` diff --git a/egs/vctk/TTS/knowledge.md b/egs/vctk/TTS/knowledge.md new file mode 100644 index 0000000000..eb1a627808 --- /dev/null +++ b/egs/vctk/TTS/knowledge.md @@ -0,0 +1,87 @@ +# VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) + +Tài liệu này giải thích các khái niệm kiến trúc, toán học và logic cốt lõi đằng sau mô hình VITS — một trong những mô hình State-of-the-Art (SOTA) trong lĩnh vực tổng hợp giọng nói. + +--- + +## 1. Sự khác biệt của VITS: End-to-End từ Text thẳng ra Waveform + +Trước thế hệ của VITS, quy trình TTS thường là một "đường ống" (pipeline) gồm 2 giai đoạn tách biệt: +1. **Acoustic Model** (Tacotron 2, FastSpeech): Biến **Text** thành **Mel-spectrogram** (dạng hình ảnh biểu diễn âm thanh tần số). +2. **Vocoder** (WaveNet, HiFi-GAN): Biến **Mel-spectrogram** thành **Waveform** (sóng âm thanh thô để phát ra loa). + +**Nhược điểm của cách cũ:** Tích tụ lỗi (Error Accumulation). Nếu Acoustic Model dự đoán Spectrogram hơi mờ, Vocoder sẽ khuyếch đại cái "mờ" đó thành tiếng nhiễu (artifacts) hoặc tiếng robot. + +🔥 **VITS giải quyết điều này bằng mô hình End-to-End:** +VITS kết nối trực tiếp Text và Waveform. Không có sự đứt gãy ở giữa. Thay vì bắt mô hình học cách tạo ra một Mel-spectrogram trung gian cứng nhắc, VITS học cách tạo ra một vùng tiềm ẩn (Latent Space) $z$. +- Từ Text, mô hình **đoán** $z$. +- Từ $z$, mô hình **tạo thẳng** ra sóng âm thanh (Waveform). +- Nếu sóng âm thanh nghe không giống thật, mô hình tự động điều chỉnh cả bộ đoán $z$ từ Text và bộ tạo âm lượng. Toàn bộ hệ thống tự tối ưu cho nhau. + +--- + +## 2. Luồng Logic (Architecture Flow) + +```mermaid +graph TD + %% Training Flow + subgraph Posterior [Posterior Encoder - Chỉ dùng lúc Train] + Audio[Audio Thật] --> Spec[Linear Spectrogram] + Spec --> PEnc[Posterior Encoder] + PEnc -- Phân phối z --> Z[Trích xuất Latent z] + end + + subgraph Prior [Prior Encoder - Đi từ Text] + Text[Phoneme Text] --> TEnc[Text Encoder] + TEnc --> MAS[Monotonic Alignment Search] + TEnc --> SDP[Stochastic Duration Predictor] + Z -- Đào tạo MAS --> MAS + MAS -- Khớp độ dài --> Flow[Normalizing Flow] + end + + subgraph Generator [Waveform Decoder] + Z -- Lúc Train --> Dec[HiFi-GAN Decoder] + Flow -- Lúc Sinh (Inference) --> Dec + Dec --> Wave[Waveform Audio] + end +``` + +**Hoạt động lúc Inference (Khi gọi `infer.py`):** +Text → Text Encoder → Normalizing Flow (biến đổi phân phối) → Decoder (sinh Waveform nhanh chóng). + +--- + +## 3. Các nền tảng Toán học & Logic cốt lõi + +VITS là sự kết hợp của 4 kỷ nguyên AI mạnh mẽ nhất: + +### A. Variational Autoencoder (VAE) +VITS xây dựng dựa trên kỹ thuật biến thiên (Variational Inference). +- Thay vì dự đoán một giá trị chính xác, mô hình dự đoán một **phân phối xác suất** (thường là phân phối chuẩn Gaussian). +- **Posterior $q(z|x)$**: Khi có âm thanh thật, mô hình giải mã nó thành các tham số $\mu, \sigma$ của $z$. +- **Prior $p(z|c)$**: Khi có text (c), mô hình dựa vào chữ cái để đoán xem âm thanh $z$ có đặc tính phân phối nào. +- Trọng tâm của toán học ở đây là **Cực đại hóa ELBO (Evidence Lower Bound)**, rút ngắn lại là giảm thiểu **KL Divergence** giữa Posterior (âm thanh thật) và Prior (text). Ép cho việc đoán từ chữ phải giống như lúc nghe âm thanh thật. + +### B. Normalizing Flows +Giọng nói con người có tính chất *One-to-Many* (Một câu nói có thể đọc trầm, bổng, vui vẻ, buồn bã). Phân phối chuẩn (Gaussian/chuông) là quá đơn giản để đại diện cho sự đa dạng này. +- **Normalizing Flows** là một chuỗi các hàm biến đổi toán học nghịch đảo (invertible functions) nhằm "nặn" một phân phối Gaussian cơ bản thành một phân phối cực kỳ phức tạp để hợp với giọng thật. +- Nó giúp Text Encoder từ một dự đoán "chung chung" trở thành một dự đoán có độ chi tiết rất cao về ngữ điệu (prosody). + +### C. Stochastic Duration Predictor (Toán học dự đoán thời lượng) +Chữ 'A' có lúc đọc dài (Aaaaa), có lúc đọc ngắn (A). +- Duration Predictor của VITS cũng dựa trên *Flow-based model* chứ không dự đoán một con số cứng nhắc dính liền với chữ. +- Nó lấy Noise ngẫu nhiên kết hợp với Text để đẻ ra thời lượng nói một cách tự nhiên. Giúp câu nói nhịp nhàng như người thật (ngắt nghỉ random). Nó dùng MLE (Maximum Likelihood Estimation) để tối ưu. + +### D. Monotonic Alignment Search (MAS) +Thuật toán tìm kiếm sự căn chỉnh **đơn điệu**. +- *Đơn điệu* nghĩa là thời gian luôn tiến tới: Bạn không thể phát âm chữ thứ 2 trước chữ thứ 1. +- MAS sử dụng thuật toán **Dynamic Programming** (Quy hoạch động - giống với Viterbi ở mô hình HMM) để tìm ra đường liên kết (alignment path) xác suất cao nhất giữa dải Spectrogram (âm thanh) và chuỗi chữ cái (Text). +- Nhờ có MAS, VITS **không cần dữ liệu gán nhãn từng mili-giây** (không cần biết chữ "Xin" dài bao nhiêu giây). Mô hình sẽ tự học cách gập (align) qua các Epoch. + +### E. Adversarial Training (Generative Adversarial Network - GAN) +Vì hàm Loss của VAE (Reconstruction Loss) có xu hướng làm âm thanh bị "mờ" và "đục", VITS dùng Decoder là một Generator của **HiFi-GAN**. +Nó setup trò chơi 2 phe: +1. **Decoder (Generator):** Tìm cách tạo âm thanh thô lừa hệ thống. +2. **Discriminator:** Cố phân biệt đâu là audio tổng hợp, đâu là audio từ ca sĩ/người đọc thật (thông qua Feature Matching Loss và LSGAN Loss). + +> VITS chính thức chấm dứt sự phụ thuộc vào các đường ống phức tạp của TTS truyền thống, sử dụng VAE để có lý thuyết thống kê liền mạch, MAS để tự học cách nối chữ và âm thanh, và GAN để Waveform tạo ra nét cắt cực khét, trong trẻo. diff --git a/egs/vctk/TTS/prepare.sh b/egs/vctk/TTS/prepare.sh index aab0753125..2b0c07ebdb 100755 --- a/egs/vctk/TTS/prepare.sh +++ b/egs/vctk/TTS/prepare.sh @@ -9,6 +9,12 @@ stage=0 stop_stage=100 use_edinburgh_vctk_url=true +# If you have VCTK already downloaded locally (e.g. from Kaggle), +# set this to the path of the existing VCTK directory to skip downloading. +# Example: +# --local-data-dir /kaggle/input/vctk-corpus +local_data_dir= + dl_dir=$PWD/download . shared/parse_options.sh || exit 1 @@ -44,8 +50,18 @@ if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then # # ln -sfv /path/to/VCTK $dl_dir/VCTK # + # Alternatively, use --local-data-dir to point to an existing VCTK directory: + # + # bash prepare.sh --local-data-dir /path/to/VCTK + # if [ ! -d $dl_dir/VCTK ]; then - lhotse download vctk --use-edinburgh-vctk-url ${use_edinburgh_vctk_url} $dl_dir + if [ -n "$local_data_dir" ]; then + log "Using local data directory: $local_data_dir" + mkdir -p $dl_dir + ln -sfv $local_data_dir $dl_dir/VCTK + else + lhotse download vctk --use-edinburgh-vctk-url ${use_edinburgh_vctk_url} $dl_dir + fi fi fi diff --git a/egs/vctk/TTS/train_from_scratch.md b/egs/vctk/TTS/train_from_scratch.md new file mode 100644 index 0000000000..be4db54177 --- /dev/null +++ b/egs/vctk/TTS/train_from_scratch.md @@ -0,0 +1,64 @@ +# Train VITS Model From Scratch + +### Cell 1: Install Dependencies +```bash +# Install icefall repo and requirements +!git clone https://github.com/k2-fsa/icefall.git /kaggle/working/icefall +!pip install -r /kaggle/working/icefall/requirements.txt +!grep -v 'numba' /kaggle/working/icefall/requirements-tts.txt | pip install -r /dev/stdin +!pip install "numba>=0.59.0" + +# Install lhotse (audio dataset toolkit) +!pip install lhotse + +# Install k2 (must match CUDA 12.8 + PyTorch 2.10.0) +!pip install k2==1.24.4.dev20260306+cuda12.8.torch2.10.0 -f https://k2-fsa.github.io/k2/cuda.html + +# Install piper_phonemize and register icefall +!pip install piper_phonemize -f https://k2-fsa.github.io/icefall/piper_phonemize.html +!pip install -e /kaggle/working/icefall +``` + +### Cell 2: Prepare Dataset +```bash +%cd /kaggle/working/icefall/egs/vctk/TTS + +# Symlink VCTK data to bypass download stage +!mkdir -p download +!ln -sfv /kaggle/input/datasets/ download/VCTK + +# Build monotonic_align C extension +!bash prepare.sh --stage -1 --stop_stage -1 + +# Create manifests, spectrograms, tokens, and data splits +!bash prepare.sh --stage 1 --stop_stage 6 +``` + +### Cell 3: Train Model +```bash +%cd /kaggle/working/icefall/egs/vctk/TTS + +!CUDA_VISIBLE_DEVICES="0" python vits/train.py \ + --world-size 1 \ + --num-epochs 1000 \ + --start-epoch 1 \ + --exp-dir vits/exp \ + --tokens data/tokens.txt \ + --max-duration 350 +``` + +### Cell 4: View TensorBoard Logs +```python +%load_ext tensorboard +%tensorboard --logdir /kaggle/working/icefall/egs/vctk/TTS/vits/exp/tensorboard +``` + +### Cell 5: Export to ONNX (After Training) +```bash +%cd /kaggle/working/icefall/egs/vctk/TTS + +!python vits/export-onnx.py \ + --epoch 1000 \ + --exp-dir vits/exp \ + --tokens data/tokens.txt +``` diff --git a/egs/vctk/TTS/vctk-vits-training.ipynb b/egs/vctk/TTS/vctk-vits-training.ipynb new file mode 100644 index 0000000000..ae8535e2b6 --- /dev/null +++ b/egs/vctk/TTS/vctk-vits-training.ipynb @@ -0,0 +1 @@ +{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"datasetVersion","sourceId":3260842,"datasetId":1975576,"databundleVersionId":3311234}],"dockerImageVersionId":31329,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!git clone https://github.com/k2-fsa/icefall.git\n%cd icefall\n!pip install -r requirements.txt\n# Install requirements-tts.txt but skip numba==0.58.1 (incompatible with Python 3.12)\n!grep -v 'numba' requirements-tts.txt | pip install -r /dev/stdin\n!pip install \"numba>=0.59.0\" # Python 3.12-compatible version\n!pip install lhotse\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:56:16.720931Z","iopub.execute_input":"2026-04-09T02:56:16.721730Z","iopub.status.idle":"2026-04-09T02:56:33.927489Z","shell.execute_reply.started":"2026-04-09T02:56:16.721693Z","shell.execute_reply":"2026-04-09T02:56:33.926654Z"}},"outputs":[{"name":"stdout","text":"Cloning into 'icefall'...\nremote: Enumerating objects: 20900, done.\u001b[K\nremote: Counting objects: 100% (90/90), done.\u001b[K\nremote: Compressing objects: 100% (68/68), done.\u001b[K\nremote: Total 20900 (delta 59), reused 22 (delta 22), pack-reused 20810 (from 3)\u001b[K\nReceiving objects: 100% (20900/20900), 25.44 MiB | 31.77 MiB/s, done.\nResolving deltas: 100% (14279/14279), done.\n/kaggle/working/icefall/egs/vctk/TTS/icefall\nRequirement already satisfied: kaldifst>1.7.0 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 1)) (1.7.17)\nRequirement already satisfied: kaldilm in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 2)) (1.15.4)\nRequirement already satisfied: kaldialign in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 3)) (0.9.3)\nRequirement already satisfied: num2words in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 4)) (0.5.14)\nRequirement already satisfied: kaldi-decoder in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 5)) (0.2.11)\nRequirement already satisfied: sentencepiece>=0.1.96 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 6)) (0.2.1)\nRequirement already satisfied: pypinyin==0.50.0 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 7)) (0.50.0)\nRequirement already satisfied: tensorboard in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 8)) (2.19.0)\nRequirement already satisfied: typeguard in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 9)) (4.5.1)\nRequirement already satisfied: dill in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 10)) (0.4.1)\nRequirement already satisfied: onnx>=1.15.0 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 11)) (1.20.1)\nRequirement already satisfied: onnxruntime>=1.16.3 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 12)) (1.24.4)\nRequirement already satisfied: onnxoptimizer in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 13)) (0.4.2)\nRequirement already satisfied: onnxsim in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 14)) (0.6.2)\nRequirement already satisfied: onnxconverter_common in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 15)) (1.16.0)\nRequirement already satisfied: black==22.3.0 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 18)) (22.3.0)\nRequirement already satisfied: isort==5.10.1 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 19)) (5.10.1)\nRequirement already satisfied: flake8==5.0.4 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 20)) (5.0.4)\nRequirement already satisfied: pycantonese==3.4.0 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 23)) (3.4.0)\nRequirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 24)) (26.0)\nRequirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r requirements.txt (line 18)) (8.3.1)\nRequirement already satisfied: platformdirs>=2 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r requirements.txt (line 18)) (4.9.2)\nRequirement already satisfied: pathspec>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r requirements.txt (line 18)) (1.0.4)\nRequirement already satisfied: mypy-extensions>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r requirements.txt (line 18)) (1.1.0)\nRequirement already satisfied: mccabe<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->-r requirements.txt (line 20)) (0.7.0)\nRequirement already satisfied: pycodestyle<2.10.0,>=2.9.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->-r requirements.txt (line 20)) (2.9.1)\nRequirement already satisfied: pyflakes<2.6.0,>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->-r requirements.txt (line 20)) (2.5.0)\nRequirement already satisfied: pylangacq<0.17.0,>=0.16.0 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->-r requirements.txt (line 23)) (0.16.2)\nRequirement already satisfied: wordseg==0.0.2 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->-r requirements.txt (line 23)) (0.0.2)\nRequirement already satisfied: docopt>=0.6.2 in /usr/local/lib/python3.12/dist-packages (from num2words->-r requirements.txt (line 4)) (0.6.2)\nRequirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (1.4.0)\nRequirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (1.78.1)\nRequirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (3.10.2)\nRequirement already satisfied: numpy>=1.12.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (1.26.4)\nRequirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (5.29.5)\nRequirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (75.2.0)\nRequirement already satisfied: six>1.9 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (1.17.0)\nRequirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (0.7.2)\nRequirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r requirements.txt (line 8)) (3.1.6)\nRequirement already satisfied: typing_extensions>=4.14.0 in /usr/local/lib/python3.12/dist-packages (from typeguard->-r requirements.txt (line 9)) (4.15.0)\nRequirement already satisfied: ml_dtypes>=0.5.0 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->-r requirements.txt (line 11)) (0.5.4)\nRequirement already satisfied: flatbuffers in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->-r requirements.txt (line 12)) (25.12.19)\nRequirement already satisfied: sympy in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->-r requirements.txt (line 12)) (1.14.0)\nRequirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from onnxsim->-r requirements.txt (line 14)) (13.9.4)\nRequirement already satisfied: python-dateutil<=3.0.0,>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (2.9.0.post0)\nRequirement already satisfied: requests<=3.0.0,>=2.18.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (2.32.4)\nRequirement already satisfied: tabulate<=0.9.0,>=0.8.9 in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (0.9.0)\nRequirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.12/dist-packages (from werkzeug>=1.0.1->tensorboard->-r requirements.txt (line 8)) (3.0.3)\nRequirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->-r requirements.txt (line 14)) (4.0.0)\nRequirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->-r requirements.txt (line 14)) (2.19.2)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy->onnxruntime>=1.16.3->-r requirements.txt (line 12)) (1.3.0)\nRequirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->onnxsim->-r requirements.txt (line 14)) (0.1.2)\nRequirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (3.4.4)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (3.11)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (2.5.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (2026.1.4)\nRequirement already satisfied: wcwidth in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r requirements.txt (line 23)) (0.6.0)\nRequirement already satisfied: matplotlib==3.8.2 in /usr/local/lib/python3.12/dist-packages (from -r /dev/stdin (line 2)) (3.8.2)\nRequirement already satisfied: cython==3.0.6 in /usr/local/lib/python3.12/dist-packages (from -r /dev/stdin (line 3)) (3.0.6)\nRequirement already satisfied: g2p_en==2.1.0 in /usr/local/lib/python3.12/dist-packages (from -r /dev/stdin (line 4)) (2.1.0)\nRequirement already satisfied: espnet_tts_frontend==0.0.3 in /usr/local/lib/python3.12/dist-packages (from -r /dev/stdin (line 5)) (0.0.3)\nRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (1.3.3)\nRequirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (0.12.1)\nRequirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (4.61.1)\nRequirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (1.4.9)\nRequirement already satisfied: numpy<2,>=1.21 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (1.26.4)\nRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (26.0)\nRequirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (11.3.0)\nRequirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (3.3.2)\nRequirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (2.9.0.post0)\nRequirement already satisfied: nltk>=3.2.4 in /usr/local/lib/python3.12/dist-packages (from g2p_en==2.1.0->-r /dev/stdin (line 4)) (3.9.1)\nRequirement already satisfied: inflect>=0.3.1 in /usr/local/lib/python3.12/dist-packages (from g2p_en==2.1.0->-r /dev/stdin (line 4)) (7.5.0)\nRequirement already satisfied: distance>=0.1.3 in /usr/local/lib/python3.12/dist-packages (from g2p_en==2.1.0->-r /dev/stdin (line 4)) (0.1.3)\nRequirement already satisfied: unidecode>=1.0.22 in /usr/local/lib/python3.12/dist-packages (from espnet_tts_frontend==0.0.3->-r /dev/stdin (line 5)) (1.4.0)\nRequirement already satisfied: jaconv in /usr/local/lib/python3.12/dist-packages (from espnet_tts_frontend==0.0.3->-r /dev/stdin (line 5)) (0.5.0)\nRequirement already satisfied: pypinyin in /usr/local/lib/python3.12/dist-packages (from espnet_tts_frontend==0.0.3->-r /dev/stdin (line 5)) (0.50.0)\nRequirement already satisfied: more_itertools>=8.5.0 in /usr/local/lib/python3.12/dist-packages (from inflect>=0.3.1->g2p_en==2.1.0->-r /dev/stdin (line 4)) (10.8.0)\nRequirement already satisfied: typeguard>=4.0.1 in /usr/local/lib/python3.12/dist-packages (from inflect>=0.3.1->g2p_en==2.1.0->-r /dev/stdin (line 4)) (4.5.1)\nRequirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (8.3.1)\nRequirement already satisfied: joblib in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (1.5.3)\nRequirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (2025.11.3)\nRequirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (4.67.3)\nRequirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.7->matplotlib==3.8.2->-r /dev/stdin (line 2)) (1.17.0)\nRequirement already satisfied: typing_extensions>=4.14.0 in /usr/local/lib/python3.12/dist-packages (from typeguard>=4.0.1->inflect>=0.3.1->g2p_en==2.1.0->-r /dev/stdin (line 4)) (4.15.0)\nRequirement already satisfied: numba>=0.59.0 in /usr/local/lib/python3.12/dist-packages (0.60.0)\nRequirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba>=0.59.0) (0.43.0)\nRequirement already satisfied: numpy<2.1,>=1.22 in /usr/local/lib/python3.12/dist-packages (from numba>=0.59.0) (1.26.4)\nCollecting lhotse\n Downloading lhotse-1.32.2-py3-none-any.whl.metadata (19 kB)\nRequirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.12/dist-packages (from lhotse) (3.1.0)\nRequirement already satisfied: SoundFile>=0.10 in /usr/local/lib/python3.12/dist-packages (from lhotse) (0.13.1)\nRequirement already satisfied: click>=7.1.1 in /usr/local/lib/python3.12/dist-packages (from lhotse) (8.3.1)\nRequirement already satisfied: cytoolz>=0.10.1 in /usr/local/lib/python3.12/dist-packages (from lhotse) (1.1.0)\nCollecting intervaltree>=3.1.0 (from lhotse)\n Downloading intervaltree-3.2.1-py2.py3-none-any.whl.metadata (12 kB)\nRequirement already satisfied: numpy>=1.18.1 in /usr/local/lib/python3.12/dist-packages (from lhotse) (1.26.4)\nRequirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from lhotse) (26.0)\nRequirement already satisfied: pyyaml>=5.3.1 in /usr/local/lib/python3.12/dist-packages (from lhotse) (6.0.3)\nRequirement already satisfied: tabulate>=0.8.1 in /usr/local/lib/python3.12/dist-packages (from lhotse) (0.9.0)\nRequirement already satisfied: torch in /usr/local/lib/python3.12/dist-packages (from lhotse) (2.10.0+cu128)\nRequirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from lhotse) (4.67.3)\nCollecting lilcom>=1.1.0 (from lhotse)\n Downloading lilcom-1.8.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (3.2 kB)\nRequirement already satisfied: toolz>=0.8.0 in /usr/local/lib/python3.12/dist-packages (from cytoolz>=0.10.1->lhotse) (0.12.1)\nRequirement already satisfied: sortedcontainers in /usr/local/lib/python3.12/dist-packages (from intervaltree>=3.1.0->lhotse) (2.4.0)\nRequirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.12/dist-packages (from SoundFile>=0.10->lhotse) (2.0.0)\nRequirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (3.24.3)\nRequirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (4.15.0)\nRequirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (75.2.0)\nRequirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (1.14.0)\nRequirement already satisfied: networkx>=2.5.1 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (3.6.1)\nRequirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (3.1.6)\nRequirement already satisfied: fsspec>=0.8.5 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (2026.2.0)\nRequirement already satisfied: cuda-bindings==12.9.4 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.9.4)\nRequirement already satisfied: nvidia-cuda-nvrtc-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.8.93)\nRequirement already satisfied: nvidia-cuda-runtime-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.8.90)\nRequirement already satisfied: nvidia-cuda-cupti-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.8.90)\nRequirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (9.10.2.21)\nRequirement already satisfied: nvidia-cublas-cu12==12.8.4.1 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.8.4.1)\nRequirement already satisfied: nvidia-cufft-cu12==11.3.3.83 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (11.3.3.83)\nRequirement already satisfied: nvidia-curand-cu12==10.3.9.90 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (10.3.9.90)\nRequirement already satisfied: nvidia-cusolver-cu12==11.7.3.90 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (11.7.3.90)\nRequirement already satisfied: nvidia-cusparse-cu12==12.5.8.93 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.5.8.93)\nRequirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (0.7.1)\nRequirement already satisfied: nvidia-nccl-cu12==2.27.5 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (2.27.5)\nRequirement already satisfied: nvidia-nvshmem-cu12==3.4.5 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (3.4.5)\nRequirement already satisfied: nvidia-nvtx-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.8.90)\nRequirement already satisfied: nvidia-nvjitlink-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (12.8.93)\nRequirement already satisfied: nvidia-cufile-cu12==1.13.1.3 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (1.13.1.3)\nRequirement already satisfied: triton==3.6.0 in /usr/local/lib/python3.12/dist-packages (from torch->lhotse) (3.6.0)\nRequirement already satisfied: cuda-pathfinder~=1.1 in /usr/local/lib/python3.12/dist-packages (from cuda-bindings==12.9.4->torch->lhotse) (1.3.5)\nRequirement already satisfied: pycparser in /usr/local/lib/python3.12/dist-packages (from cffi>=1.0->SoundFile>=0.10->lhotse) (3.0)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch->lhotse) (1.3.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch->lhotse) (3.0.3)\nDownloading lhotse-1.32.2-py3-none-any.whl (889 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m889.7/889.7 kB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n\u001b[?25hDownloading intervaltree-3.2.1-py2.py3-none-any.whl (25 kB)\nDownloading lilcom-1.8.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (92 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.0/93.0 kB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hInstalling collected packages: lilcom, intervaltree, lhotse\nSuccessfully installed intervaltree-3.2.1 lhotse-1.32.2 lilcom-1.8.2\n","output_type":"stream"}],"execution_count":8},{"cell_type":"code","source":"%cd /kaggle/working/icefall/egs/vctk/TTS\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:12:46.649658Z","iopub.execute_input":"2026-04-09T02:12:46.649960Z","iopub.status.idle":"2026-04-09T02:12:46.656758Z","shell.execute_reply.started":"2026-04-09T02:12:46.649927Z","shell.execute_reply":"2026-04-09T02:12:46.655782Z"}},"outputs":[{"name":"stdout","text":"/kaggle/working/icefall/egs/vctk/TTS\n","output_type":"stream"}],"execution_count":2},{"cell_type":"code","source":"!bash ./prepare.sh\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:12:46.658034Z","iopub.execute_input":"2026-04-09T02:12:46.658416Z","iopub.status.idle":"2026-04-09T02:12:55.132064Z","shell.execute_reply.started":"2026-04-09T02:12:46.658377Z","shell.execute_reply":"2026-04-09T02:12:55.131151Z"}},"outputs":[{"name":"stdout","text":"2026-04-09 02:12:46 (prepare.sh:26:main) dl_dir: /kaggle/working/icefall/egs/vctk/TTS/download\n2026-04-09 02:12:46 (prepare.sh:40:main) Stage 0: Download data\nTraceback (most recent call last):\n File \"/usr/local/bin/lhotse\", line 8, in \n sys.exit(cli())\n ^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/click/core.py\", line 1485, in __call__\n return self.main(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/click/core.py\", line 1406, in main\n rv = self.invoke(ctx)\n ^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/click/core.py\", line 1873, in invoke\n return _process_result(sub_ctx.command.invoke(sub_ctx))\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/click/core.py\", line 1873, in invoke\n return _process_result(sub_ctx.command.invoke(sub_ctx))\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/click/core.py\", line 1269, in invoke\n return ctx.invoke(self.callback, **ctx.params)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/click/core.py\", line 824, in invoke\n return callback(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/bin/modes/recipes/vctk.py\", line 26, in vctk\n download_vctk(target_dir, use_edinburgh_vctk_url=use_edinburgh_vctk_url)\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/recipes/vctk.py\", line 131, in download_vctk\n resumable_download(\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/utils.py\", line 569, in resumable_download\n raise e\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/utils.py\", line 537, in resumable_download\n _download(req, file_size)\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/utils.py\", line 519, in _download\n with urllib.request.urlopen(rq, context=ssl_context) as response:\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/lib/python3.12/urllib/request.py\", line 215, in urlopen\n return opener.open(url, data, timeout)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/lib/python3.12/urllib/request.py\", line 521, in open\n response = meth(req, response)\n ^^^^^^^^^^^^^^^^^^^\n File \"/usr/lib/python3.12/urllib/request.py\", line 630, in http_response\n response = self.parent.error(\n ^^^^^^^^^^^^^^^^^^\n File \"/usr/lib/python3.12/urllib/request.py\", line 559, in error\n return self._call_chain(*args)\n ^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/lib/python3.12/urllib/request.py\", line 492, in _call_chain\n result = func(*args)\n ^^^^^^^^^^^\n File \"/usr/lib/python3.12/urllib/request.py\", line 639, in http_error_default\n raise HTTPError(req.full_url, code, msg, hdrs, fp)\nurllib.error.HTTPError: HTTP Error 403: Forbidden\n","output_type":"stream"}],"execution_count":3},{"cell_type":"code","source":"import os, glob\nvctk_paths = glob.glob(\"/kaggle/input/*/\")\nprint(\"Available datasets:\", vctk_paths) # find the right path\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:12:55.133572Z","iopub.execute_input":"2026-04-09T02:12:55.134073Z","iopub.status.idle":"2026-04-09T02:12:55.140109Z","shell.execute_reply.started":"2026-04-09T02:12:55.134039Z","shell.execute_reply":"2026-04-09T02:12:55.139322Z"}},"outputs":[{"name":"stdout","text":"Available datasets: ['/kaggle/input/datasets/']\n","output_type":"stream"}],"execution_count":4},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nprint(\"PyTorch:\", torch.__version__) # should show 2.10.0+cu128\nprint(\"CUDA:\", torch.version.cuda) # should show 12.8","metadata":{"trusted":true},"outputs":[{"name":"stdout","text":"PyTorch: 2.10.0+cu128\nCUDA: 12.8\n","output_type":"stream"}],"execution_count":5},{"cell_type":"code","source":"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:16:01.156658Z","iopub.execute_input":"2026-04-09T02:16:01.157882Z","iopub.status.idle":"2026-04-09T02:16:11.493673Z","shell.execute_reply.started":"2026-04-09T02:16:01.157844Z","shell.execute_reply":"2026-04-09T02:16:11.492395Z"}},"outputs":[{"name":"stdout","text":"Looking in links: https://k2-fsa.github.io/k2/cuda.html\nCollecting k2==1.24.4.dev20260306+cuda12.8.torch2.10.0\n Downloading https://huggingface.co/csukuangfj2/k2/resolve/main/ubuntu-cuda/k2-1.24.4.dev20260306%2Bcuda12.8.torch2.10.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (176.8 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m176.8/176.8 MB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hRequirement already satisfied: torch==2.10.0 in /usr/local/lib/python3.12/dist-packages (from k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2.10.0+cu128)\nRequirement already satisfied: graphviz in /usr/local/lib/python3.12/dist-packages (from k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (0.21)\nRequirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.24.3)\nRequirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (4.15.0)\nRequirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (75.2.0)\nRequirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.14.0)\nRequirement already satisfied: networkx>=2.5.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.6.1)\nRequirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.1.6)\nRequirement already satisfied: fsspec>=0.8.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2026.2.0)\nRequirement already satisfied: cuda-bindings==12.9.4 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.9.4)\nRequirement already satisfied: nvidia-cuda-nvrtc-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.93)\nRequirement already satisfied: nvidia-cuda-runtime-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-cuda-cupti-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (9.10.2.21)\nRequirement already satisfied: nvidia-cublas-cu12==12.8.4.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.4.1)\nRequirement already satisfied: nvidia-cufft-cu12==11.3.3.83 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (11.3.3.83)\nRequirement already satisfied: nvidia-curand-cu12==10.3.9.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (10.3.9.90)\nRequirement already satisfied: nvidia-cusolver-cu12==11.7.3.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (11.7.3.90)\nRequirement already satisfied: nvidia-cusparse-cu12==12.5.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.5.8.93)\nRequirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (0.7.1)\nRequirement already satisfied: nvidia-nccl-cu12==2.27.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2.27.5)\nRequirement already satisfied: nvidia-nvshmem-cu12==3.4.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.4.5)\nRequirement already satisfied: nvidia-nvtx-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-nvjitlink-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.93)\nRequirement already satisfied: nvidia-cufile-cu12==1.13.1.3 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.13.1.3)\nRequirement already satisfied: triton==3.6.0 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.6.0)\nRequirement already satisfied: cuda-pathfinder~=1.1 in /usr/local/lib/python3.12/dist-packages (from cuda-bindings==12.9.4->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.3.5)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.3.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.0.3)\nInstalling collected packages: k2\nSuccessfully installed k2-1.24.4.dev20260306+cuda12.8.torch2.10.0\n","output_type":"stream"}],"execution_count":6},{"cell_type":"code","source":"!pip install piper_phonemize -f https://k2-fsa.github.io/icefall/piper_phonemize.html\n\n!pip install -e /kaggle/working/icefall\n\n%cd /kaggle/working/icefall/egs/vctk/TTS\n\n!CUDA_VISIBLE_DEVICES=\"0\" python vits/train.py \\\n --world-size 1 \\\n --num-epochs 1000 \\\n --start-epoch 1 \\\n --exp-dir vits/exp \\\n --tokens data/tokens.txt \\\n --max-duration 350\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:20:23.146081Z","iopub.execute_input":"2026-04-09T02:20:23.146884Z","iopub.status.idle":"2026-04-09T02:20:54.919919Z","shell.execute_reply.started":"2026-04-09T02:20:23.146843Z","shell.execute_reply":"2026-04-09T02:20:54.918675Z"}},"outputs":[{"name":"stdout","text":"Looking in links: https://k2-fsa.github.io/icefall/piper_phonemize.html\nRequirement already satisfied: piper_phonemize in /usr/local/lib/python3.12/dist-packages (1.3.0)\nObtaining file:///kaggle/working/icefall\n Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n Checking if build backend supports build_editable ... \u001b[?25l\u001b[?25hdone\n Getting requirements to build editable ... \u001b[?25l\u001b[?25hdone\n Preparing editable metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\nRequirement already satisfied: kaldifst>1.7.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.7.17)\nRequirement already satisfied: kaldilm in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.15.4)\nRequirement already satisfied: kaldialign in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.9.3)\nRequirement already satisfied: num2words in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.5.14)\nRequirement already satisfied: kaldi-decoder in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.2.11)\nRequirement already satisfied: sentencepiece>=0.1.96 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.2.1)\nRequirement already satisfied: pypinyin==0.50.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.50.0)\nRequirement already satisfied: tensorboard in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (2.19.0)\nRequirement already satisfied: typeguard in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (4.5.1)\nRequirement already satisfied: dill in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.4.1)\nRequirement already satisfied: onnx>=1.15.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.20.1)\nRequirement already satisfied: onnxruntime>=1.16.3 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.24.4)\nRequirement already satisfied: onnxoptimizer in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.4.2)\nRequirement already satisfied: onnxsim in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.6.2)\nRequirement already satisfied: onnxconverter_common in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.16.0)\nRequirement already satisfied: black==22.3.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (22.3.0)\nRequirement already satisfied: isort==5.10.1 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (5.10.1)\nRequirement already satisfied: flake8==5.0.4 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (5.0.4)\nRequirement already satisfied: pycantonese==3.4.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (3.4.0)\nRequirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (26.0)\nRequirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (8.3.1)\nRequirement already satisfied: platformdirs>=2 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (4.9.2)\nRequirement already satisfied: pathspec>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (1.0.4)\nRequirement already satisfied: mypy-extensions>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (1.1.0)\nRequirement already satisfied: mccabe<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (0.7.0)\nRequirement already satisfied: pycodestyle<2.10.0,>=2.9.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (2.9.1)\nRequirement already satisfied: pyflakes<2.6.0,>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (2.5.0)\nRequirement already satisfied: pylangacq<0.17.0,>=0.16.0 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->icefall==1.0) (0.16.2)\nRequirement already satisfied: wordseg==0.0.2 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->icefall==1.0) (0.0.2)\nRequirement already satisfied: numpy>=1.23.2 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (1.26.4)\nRequirement already satisfied: protobuf>=4.25.1 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (5.29.5)\nRequirement already satisfied: typing_extensions>=4.7.1 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (4.15.0)\nRequirement already satisfied: ml_dtypes>=0.5.0 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (0.5.4)\nRequirement already satisfied: flatbuffers in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->icefall==1.0) (25.12.19)\nRequirement already satisfied: sympy in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->icefall==1.0) (1.14.0)\nRequirement already satisfied: docopt>=0.6.2 in /usr/local/lib/python3.12/dist-packages (from num2words->icefall==1.0) (0.6.2)\nRequirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from onnxsim->icefall==1.0) (13.9.4)\nRequirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.4.0)\nRequirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.78.1)\nRequirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (3.10.2)\nRequirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (75.2.0)\nRequirement already satisfied: six>1.9 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.17.0)\nRequirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (0.7.2)\nRequirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (3.1.6)\nRequirement already satisfied: python-dateutil<=3.0.0,>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.9.0.post0)\nRequirement already satisfied: requests<=3.0.0,>=2.18.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.32.4)\nRequirement already satisfied: tabulate<=0.9.0,>=0.8.9 in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (0.9.0)\nRequirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.12/dist-packages (from werkzeug>=1.0.1->tensorboard->icefall==1.0) (3.0.3)\nRequirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->icefall==1.0) (4.0.0)\nRequirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->icefall==1.0) (2.19.2)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy->onnxruntime>=1.16.3->icefall==1.0) (1.3.0)\nRequirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->onnxsim->icefall==1.0) (0.1.2)\nRequirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (3.4.4)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (3.11)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.5.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2026.1.4)\nRequirement already satisfied: wcwidth in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (0.6.0)\nBuilding wheels for collected packages: icefall\n Building editable for icefall (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n Created wheel for icefall: filename=icefall-1.0-0.editable-py3-none-any.whl size=7298 sha256=f774149d32d0d1984c76276c94223985434a63642a02313f0882cf129a28c7e7\n Stored in directory: /tmp/pip-ephem-wheel-cache-_fo47oi1/wheels/15/7d/60/a461439407a382249acfd8d18f7237475e164801218e112983\nSuccessfully built icefall\nInstalling collected packages: icefall\nSuccessfully installed icefall-1.0\n/kaggle/working/icefall/egs/vctk/TTS\n2026-04-09 02:20:44.835985: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\nWARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nE0000 00:00:1775701244.864399 258 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\nE0000 00:00:1775701244.875416 258 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\nW0000 00:00:1775701244.896746 258 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\nW0000 00:00:1775701244.896796 258 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\nW0000 00:00:1775701244.896803 258 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\nW0000 00:00:1775701244.896812 258 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n/kaggle/working/icefall/icefall/utils.py:1664: SyntaxWarning: invalid escape sequence '\\d'\n \\delta = \\frac{\\Vert\\theta - \\theta_{new}\\Vert^2}{\\Vert\\theta\\Vert^2}\n2026-04-09 02:20:52,859 INFO [train.py:805] Training started\n2026-04-09 02:20:52,861 INFO [train.py:815] Device: cuda:0\nTraceback (most recent call last):\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/train.py\", line 1002, in \n main()\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/train.py\", line 995, in main\n run(rank=0, world_size=1, args=args)\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/train.py\", line 817, in run\n tokenizer = Tokenizer(params.tokens)\n ^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/tokenizer.py\", line 41, in __init__\n with open(tokens, \"r\", encoding=\"utf-8\") as f:\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nFileNotFoundError: [Errno 2] No such file or directory: 'data/tokens.txt'\n","output_type":"stream"}],"execution_count":14},{"cell_type":"code","source":"!pip install k2==1.24.4.dev20260306+cuda12.8.torch2.10.0 \\\n -f https://k2-fsa.github.io/k2/cuda.html\n\n!pip install piper_phonemize \\\n -f https://k2-fsa.github.io/icefall/piper_phonemize.html\n\n!pip install -e /kaggle/working/icefall\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:25:22.526325Z","iopub.execute_input":"2026-04-09T02:25:22.526990Z","iopub.status.idle":"2026-04-09T02:25:43.577562Z","shell.execute_reply.started":"2026-04-09T02:25:22.526950Z","shell.execute_reply":"2026-04-09T02:25:43.576549Z"}},"outputs":[{"name":"stdout","text":"Looking in links: https://k2-fsa.github.io/k2/cuda.html\nRequirement already satisfied: k2==1.24.4.dev20260306+cuda12.8.torch2.10.0 in /usr/local/lib/python3.12/dist-packages (1.24.4.dev20260306+cuda12.8.torch2.10.0)\nRequirement already satisfied: torch==2.10.0 in /usr/local/lib/python3.12/dist-packages (from k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2.10.0+cu128)\nRequirement already satisfied: graphviz in /usr/local/lib/python3.12/dist-packages (from k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (0.21)\nRequirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.24.3)\nRequirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (4.15.0)\nRequirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (75.2.0)\nRequirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.14.0)\nRequirement already satisfied: networkx>=2.5.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.6.1)\nRequirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.1.6)\nRequirement already satisfied: fsspec>=0.8.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2026.2.0)\nRequirement already satisfied: cuda-bindings==12.9.4 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.9.4)\nRequirement already satisfied: nvidia-cuda-nvrtc-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.93)\nRequirement already satisfied: nvidia-cuda-runtime-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-cuda-cupti-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (9.10.2.21)\nRequirement already satisfied: nvidia-cublas-cu12==12.8.4.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.4.1)\nRequirement already satisfied: nvidia-cufft-cu12==11.3.3.83 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (11.3.3.83)\nRequirement already satisfied: nvidia-curand-cu12==10.3.9.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (10.3.9.90)\nRequirement already satisfied: nvidia-cusolver-cu12==11.7.3.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (11.7.3.90)\nRequirement already satisfied: nvidia-cusparse-cu12==12.5.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.5.8.93)\nRequirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (0.7.1)\nRequirement already satisfied: nvidia-nccl-cu12==2.27.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2.27.5)\nRequirement already satisfied: nvidia-nvshmem-cu12==3.4.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.4.5)\nRequirement already satisfied: nvidia-nvtx-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-nvjitlink-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.93)\nRequirement already satisfied: nvidia-cufile-cu12==1.13.1.3 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.13.1.3)\nRequirement already satisfied: triton==3.6.0 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.6.0)\nRequirement already satisfied: cuda-pathfinder~=1.1 in /usr/local/lib/python3.12/dist-packages (from cuda-bindings==12.9.4->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.3.5)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.3.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.0.3)\nLooking in links: https://k2-fsa.github.io/icefall/piper_phonemize.html\nRequirement already satisfied: piper_phonemize in /usr/local/lib/python3.12/dist-packages (1.3.0)\nObtaining file:///kaggle/working/icefall\n Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n Checking if build backend supports build_editable ... \u001b[?25l\u001b[?25hdone\n Getting requirements to build editable ... \u001b[?25l\u001b[?25hdone\n Preparing editable metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\nRequirement already satisfied: kaldifst>1.7.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.7.17)\nRequirement already satisfied: kaldilm in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.15.4)\nRequirement already satisfied: kaldialign in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.9.3)\nRequirement already satisfied: num2words in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.5.14)\nRequirement already satisfied: kaldi-decoder in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.2.11)\nRequirement already satisfied: sentencepiece>=0.1.96 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.2.1)\nRequirement already satisfied: pypinyin==0.50.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.50.0)\nRequirement already satisfied: tensorboard in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (2.19.0)\nRequirement already satisfied: typeguard in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (4.5.1)\nRequirement already satisfied: dill in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.4.1)\nRequirement already satisfied: onnx>=1.15.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.20.1)\nRequirement already satisfied: onnxruntime>=1.16.3 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.24.4)\nRequirement already satisfied: onnxoptimizer in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.4.2)\nRequirement already satisfied: onnxsim in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.6.2)\nRequirement already satisfied: onnxconverter_common in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.16.0)\nRequirement already satisfied: black==22.3.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (22.3.0)\nRequirement already satisfied: isort==5.10.1 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (5.10.1)\nRequirement already satisfied: flake8==5.0.4 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (5.0.4)\nRequirement already satisfied: pycantonese==3.4.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (3.4.0)\nRequirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (26.0)\nRequirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (8.3.1)\nRequirement already satisfied: platformdirs>=2 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (4.9.2)\nRequirement already satisfied: pathspec>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (1.0.4)\nRequirement already satisfied: mypy-extensions>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (1.1.0)\nRequirement already satisfied: mccabe<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (0.7.0)\nRequirement already satisfied: pycodestyle<2.10.0,>=2.9.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (2.9.1)\nRequirement already satisfied: pyflakes<2.6.0,>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (2.5.0)\nRequirement already satisfied: pylangacq<0.17.0,>=0.16.0 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->icefall==1.0) (0.16.2)\nRequirement already satisfied: wordseg==0.0.2 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->icefall==1.0) (0.0.2)\nRequirement already satisfied: numpy>=1.23.2 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (1.26.4)\nRequirement already satisfied: protobuf>=4.25.1 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (5.29.5)\nRequirement already satisfied: typing_extensions>=4.7.1 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (4.15.0)\nRequirement already satisfied: ml_dtypes>=0.5.0 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (0.5.4)\nRequirement already satisfied: flatbuffers in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->icefall==1.0) (25.12.19)\nRequirement already satisfied: sympy in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->icefall==1.0) (1.14.0)\nRequirement already satisfied: docopt>=0.6.2 in /usr/local/lib/python3.12/dist-packages (from num2words->icefall==1.0) (0.6.2)\nRequirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from onnxsim->icefall==1.0) (13.9.4)\nRequirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.4.0)\nRequirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.78.1)\nRequirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (3.10.2)\nRequirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (75.2.0)\nRequirement already satisfied: six>1.9 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.17.0)\nRequirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (0.7.2)\nRequirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (3.1.6)\nRequirement already satisfied: python-dateutil<=3.0.0,>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.9.0.post0)\nRequirement already satisfied: requests<=3.0.0,>=2.18.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.32.4)\nRequirement already satisfied: tabulate<=0.9.0,>=0.8.9 in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (0.9.0)\nRequirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.12/dist-packages (from werkzeug>=1.0.1->tensorboard->icefall==1.0) (3.0.3)\nRequirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->icefall==1.0) (4.0.0)\nRequirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->icefall==1.0) (2.19.2)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy->onnxruntime>=1.16.3->icefall==1.0) (1.3.0)\nRequirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->onnxsim->icefall==1.0) (0.1.2)\nRequirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (3.4.4)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (3.11)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.5.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2026.1.4)\nRequirement already satisfied: wcwidth in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (0.6.0)\nBuilding wheels for collected packages: icefall\n Building editable for icefall (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n Created wheel for icefall: filename=icefall-1.0-0.editable-py3-none-any.whl size=7298 sha256=0059c5cbba953bf699d1bbac5d2ebc5d2eb84a43168f4f8d87080739119e8738\n Stored in directory: /tmp/pip-ephem-wheel-cache-yflj7q9b/wheels/15/7d/60/a461439407a382249acfd8d18f7237475e164801218e112983\nSuccessfully built icefall\nInstalling collected packages: icefall\n Attempting uninstall: icefall\n Found existing installation: icefall 1.0\n Uninstalling icefall-1.0:\n Successfully uninstalled icefall-1.0\nSuccessfully installed icefall-1.0\n","output_type":"stream"}],"execution_count":15},{"cell_type":"code","source":"!git clone https://github.com/k2-fsa/icefall /kaggle/working/icefall\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:25:44.761664Z","iopub.execute_input":"2026-04-09T02:25:44.762361Z","iopub.status.idle":"2026-04-09T02:25:44.897763Z","shell.execute_reply.started":"2026-04-09T02:25:44.762321Z","shell.execute_reply":"2026-04-09T02:25:44.896798Z"}},"outputs":[{"name":"stdout","text":"fatal: destination path '/kaggle/working/icefall' already exists and is not an empty directory.\n","output_type":"stream"}],"execution_count":16},{"cell_type":"code","source":"from huggingface_hub import hf_hub_download\nimport os\n\nMODEL_ID = \"zrjin/icefall-tts-vctk-vits-2023-12-05\"\nEXP_DIR = \"/kaggle/working/icefall/egs/vctk/TTS/vits/exp\"\nDATA_DIR = \"/kaggle/working/icefall/egs/vctk/TTS/data\"\n\nos.makedirs(EXP_DIR, exist_ok=True)\nos.makedirs(DATA_DIR, exist_ok=True)\n\nhf_hub_download(\n repo_id=MODEL_ID,\n filename=\"exp/epoch-1000.pt\",\n local_dir=\"/kaggle/working/icefall/egs/vctk/TTS\"\n)\n\nhf_hub_download(\n repo_id=MODEL_ID,\n filename=\"data/tokens.txt\",\n local_dir=\"/kaggle/working/icefall/egs/vctk/TTS\"\n)\n\nprint(\"✅ Download xong!\")\nprint(f\" Checkpoint: {EXP_DIR}/epoch-1000.pt\")\nprint(f\" Tokens: {DATA_DIR}/tokens.txt\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:25:54.416127Z","iopub.execute_input":"2026-04-09T02:25:54.417106Z","iopub.status.idle":"2026-04-09T02:26:05.933908Z","shell.execute_reply.started":"2026-04-09T02:25:54.417064Z","shell.execute_reply":"2026-04-09T02:26:05.932635Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"exp/epoch-1000.pt: 0%| | 0.00/1.08G [00:00\n main()\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/train.py\", line 995, in main\n run(rank=0, world_size=1, args=args)\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/train.py\", line 817, in run\n tokenizer = Tokenizer(params.tokens)\n ^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/tokenizer.py\", line 54, in __init__\n self.pad_id = self.token2id[\"_\"] # padding\n ~~~~~~~~~~~~~^^^^^\nKeyError: '_'\n","output_type":"stream"}],"execution_count":22},{"cell_type":"markdown","source":"# Run Inference with Pretrained Model","metadata":{}},{"cell_type":"code","source":"\n# Install icefall repo\n!git clone https://github.com/k2-fsa/icefall.git /kaggle/working/icefall\n!pip install -r /kaggle/working/icefall/requirements.txt\n!grep -v 'numba' /kaggle/working/icefall/requirements-tts.txt | pip install -r /dev/stdin\n!pip install \"numba>=0.59.0\"\n\n# Register icefall as Python package so \"import icefall\" works\n!pip install -e /kaggle/working/icefall\n\n# Install phonemizer used by VITS\n!pip install piper_phonemize -f https://k2-fsa.github.io/icefall/piper_phonemize.html","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:52:44.255307Z","iopub.execute_input":"2026-04-09T02:52:44.255523Z","iopub.status.idle":"2026-04-09T02:54:08.723837Z","shell.execute_reply.started":"2026-04-09T02:52:44.255494Z","shell.execute_reply":"2026-04-09T02:54:08.723063Z"}},"outputs":[{"name":"stdout","text":"Cloning into '/kaggle/working/icefall'...\nremote: Enumerating objects: 20900, done.\u001b[K\nremote: Counting objects: 100% (90/90), done.\u001b[K\nremote: Compressing objects: 100% (68/68), done.\u001b[K\nremote: Total 20900 (delta 59), reused 22 (delta 22), pack-reused 20810 (from 3)\u001b[K\nReceiving objects: 100% (20900/20900), 25.44 MiB | 27.34 MiB/s, done.\nResolving deltas: 100% (14279/14279), done.\nCollecting kaldifst>1.7.0 (from -r /kaggle/working/icefall/requirements.txt (line 1))\n Downloading kaldifst-1.7.17-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (1.0 kB)\nCollecting kaldilm (from -r /kaggle/working/icefall/requirements.txt (line 2))\n Downloading kaldilm-1.15.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl.metadata (9.2 kB)\nCollecting kaldialign (from -r /kaggle/working/icefall/requirements.txt (line 3))\n Downloading kaldialign-0.9.3-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl.metadata (4.4 kB)\nCollecting num2words (from -r /kaggle/working/icefall/requirements.txt (line 4))\n Downloading num2words-0.5.14-py3-none-any.whl.metadata (13 kB)\nCollecting kaldi-decoder (from -r /kaggle/working/icefall/requirements.txt (line 5))\n Downloading kaldi_decoder-0.2.11-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (1.4 kB)\nRequirement already satisfied: sentencepiece>=0.1.96 in /usr/local/lib/python3.12/dist-packages (from -r /kaggle/working/icefall/requirements.txt (line 6)) (0.2.1)\nCollecting pypinyin==0.50.0 (from -r /kaggle/working/icefall/requirements.txt (line 7))\n Downloading pypinyin-0.50.0-py2.py3-none-any.whl.metadata (12 kB)\nRequirement already satisfied: tensorboard in /usr/local/lib/python3.12/dist-packages (from -r /kaggle/working/icefall/requirements.txt (line 8)) (2.19.0)\nRequirement already satisfied: typeguard in /usr/local/lib/python3.12/dist-packages (from -r /kaggle/working/icefall/requirements.txt (line 9)) (4.5.1)\nRequirement already satisfied: dill in /usr/local/lib/python3.12/dist-packages (from -r /kaggle/working/icefall/requirements.txt (line 10)) (0.4.1)\nRequirement already satisfied: onnx>=1.15.0 in /usr/local/lib/python3.12/dist-packages (from -r /kaggle/working/icefall/requirements.txt (line 11)) (1.20.1)\nCollecting onnxruntime>=1.16.3 (from -r /kaggle/working/icefall/requirements.txt (line 12))\n Downloading onnxruntime-1.24.4-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (5.2 kB)\nCollecting onnxoptimizer (from -r /kaggle/working/icefall/requirements.txt (line 13))\n Downloading onnxoptimizer-0.4.2-cp312-abi3-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl.metadata (3.1 kB)\nCollecting onnxsim (from -r /kaggle/working/icefall/requirements.txt (line 14))\n Downloading onnxsim-0.6.2-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (4.5 kB)\nCollecting onnxconverter_common (from -r /kaggle/working/icefall/requirements.txt (line 15))\n Downloading onnxconverter_common-1.16.0-py2.py3-none-any.whl.metadata (4.8 kB)\nCollecting black==22.3.0 (from -r /kaggle/working/icefall/requirements.txt (line 18))\n Downloading black-22.3.0-py3-none-any.whl.metadata (45 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.6/45.6 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hCollecting isort==5.10.1 (from -r /kaggle/working/icefall/requirements.txt (line 19))\n Downloading isort-5.10.1-py3-none-any.whl.metadata (12 kB)\nCollecting flake8==5.0.4 (from -r /kaggle/working/icefall/requirements.txt (line 20))\n Downloading flake8-5.0.4-py2.py3-none-any.whl.metadata (4.1 kB)\nCollecting pycantonese==3.4.0 (from -r /kaggle/working/icefall/requirements.txt (line 23))\n Downloading pycantonese-3.4.0-py3-none-any.whl.metadata (6.8 kB)\nRequirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from -r /kaggle/working/icefall/requirements.txt (line 24)) (26.0)\nRequirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r /kaggle/working/icefall/requirements.txt (line 18)) (8.3.1)\nRequirement already satisfied: platformdirs>=2 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r /kaggle/working/icefall/requirements.txt (line 18)) (4.9.2)\nRequirement already satisfied: pathspec>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r /kaggle/working/icefall/requirements.txt (line 18)) (1.0.4)\nRequirement already satisfied: mypy-extensions>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->-r /kaggle/working/icefall/requirements.txt (line 18)) (1.1.0)\nCollecting mccabe<0.8.0,>=0.7.0 (from flake8==5.0.4->-r /kaggle/working/icefall/requirements.txt (line 20))\n Downloading mccabe-0.7.0-py2.py3-none-any.whl.metadata (5.0 kB)\nCollecting pycodestyle<2.10.0,>=2.9.0 (from flake8==5.0.4->-r /kaggle/working/icefall/requirements.txt (line 20))\n Downloading pycodestyle-2.9.1-py2.py3-none-any.whl.metadata (31 kB)\nCollecting pyflakes<2.6.0,>=2.5.0 (from flake8==5.0.4->-r /kaggle/working/icefall/requirements.txt (line 20))\n Downloading pyflakes-2.5.0-py2.py3-none-any.whl.metadata (3.8 kB)\nCollecting pylangacq<0.17.0,>=0.16.0 (from pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23))\n Downloading pylangacq-0.16.2-py3-none-any.whl.metadata (5.8 kB)\nCollecting wordseg==0.0.2 (from pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23))\n Downloading wordseg-0.0.2-py3-none-any.whl.metadata (4.8 kB)\nCollecting docopt>=0.6.2 (from num2words->-r /kaggle/working/icefall/requirements.txt (line 4))\n Downloading docopt-0.6.2.tar.gz (25 kB)\n Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\nRequirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (1.4.0)\nRequirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (1.78.1)\nRequirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (3.10.2)\nRequirement already satisfied: numpy>=1.12.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (2.0.2)\nRequirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (5.29.5)\nRequirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (75.2.0)\nRequirement already satisfied: six>1.9 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (1.17.0)\nRequirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (0.7.2)\nRequirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (3.1.6)\nRequirement already satisfied: typing_extensions>=4.14.0 in /usr/local/lib/python3.12/dist-packages (from typeguard->-r /kaggle/working/icefall/requirements.txt (line 9)) (4.15.0)\nRequirement already satisfied: ml_dtypes>=0.5.0 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->-r /kaggle/working/icefall/requirements.txt (line 11)) (0.5.4)\nRequirement already satisfied: flatbuffers in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->-r /kaggle/working/icefall/requirements.txt (line 12)) (25.12.19)\nRequirement already satisfied: sympy in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->-r /kaggle/working/icefall/requirements.txt (line 12)) (1.14.0)\nRequirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from onnxsim->-r /kaggle/working/icefall/requirements.txt (line 14)) (13.9.4)\nRequirement already satisfied: python-dateutil<=3.0.0,>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (2.9.0.post0)\nRequirement already satisfied: requests<=3.0.0,>=2.18.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (2.32.4)\nRequirement already satisfied: tabulate<=0.9.0,>=0.8.9 in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (0.9.0)\nRequirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.12/dist-packages (from werkzeug>=1.0.1->tensorboard->-r /kaggle/working/icefall/requirements.txt (line 8)) (3.0.3)\nRequirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->-r /kaggle/working/icefall/requirements.txt (line 14)) (4.0.0)\nRequirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->-r /kaggle/working/icefall/requirements.txt (line 14)) (2.19.2)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy->onnxruntime>=1.16.3->-r /kaggle/working/icefall/requirements.txt (line 12)) (1.3.0)\nRequirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->onnxsim->-r /kaggle/working/icefall/requirements.txt (line 14)) (0.1.2)\nRequirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (3.4.4)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (3.11)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (2.5.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (2026.1.4)\nRequirement already satisfied: wcwidth in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->-r /kaggle/working/icefall/requirements.txt (line 23)) (0.6.0)\nDownloading pypinyin-0.50.0-py2.py3-none-any.whl (1.4 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.4/1.4 MB\u001b[0m \u001b[31m21.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n\u001b[?25hDownloading black-22.3.0-py3-none-any.whl (153 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m153.9/153.9 kB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading isort-5.10.1-py3-none-any.whl (103 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m103.4/103.4 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading flake8-5.0.4-py2.py3-none-any.whl (61 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.9/61.9 kB\u001b[0m \u001b[31m4.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading pycantonese-3.4.0-py3-none-any.whl (3.9 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.9/3.9 MB\u001b[0m \u001b[31m80.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n\u001b[?25hDownloading wordseg-0.0.2-py3-none-any.whl (9.5 kB)\nDownloading kaldifst-1.7.17-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (5.6 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.6/5.6 MB\u001b[0m \u001b[31m58.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m:00:01\u001b[0m\n\u001b[?25hDownloading kaldilm-1.15.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (571 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m571.4/571.4 kB\u001b[0m \u001b[31m28.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading kaldialign-0.9.3-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (77 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.7/77.7 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading num2words-0.5.14-py3-none-any.whl (163 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m163.5/163.5 kB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading kaldi_decoder-0.2.11-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (608 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m608.3/608.3 kB\u001b[0m \u001b[31m28.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading onnxruntime-1.24.4-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (17.2 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.2/17.2 MB\u001b[0m \u001b[31m84.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading onnxoptimizer-0.4.2-cp312-abi3-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (1.0 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m40.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading onnxsim-0.6.2-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (2.9 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.9/2.9 MB\u001b[0m \u001b[31m74.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n\u001b[?25hDownloading onnxconverter_common-1.16.0-py2.py3-none-any.whl (89 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m89.5/89.5 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading mccabe-0.7.0-py2.py3-none-any.whl (7.3 kB)\nDownloading pycodestyle-2.9.1-py2.py3-none-any.whl (41 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.5/41.5 kB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading pyflakes-2.5.0-py2.py3-none-any.whl (66 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m66.1/66.1 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading pylangacq-0.16.2-py3-none-any.whl (64 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.5/64.5 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hBuilding wheels for collected packages: docopt\n Building wheel for docopt (setup.py) ... \u001b[?25l\u001b[?25hdone\n Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=e3eb7cd71c73894a683ad1dd1129b3c32978925b50ca1be50999b91d96e9051f\n Stored in directory: /root/.cache/pip/wheels/1a/bf/a1/4cee4f7678c68c5875ca89eaccf460593539805c3906722228\nSuccessfully built docopt\nInstalling collected packages: kaldialign, docopt, wordseg, pypinyin, pyflakes, pycodestyle, num2words, mccabe, kaldilm, kaldifst, kaldi-decoder, isort, black, pylangacq, onnxruntime, flake8, pycantonese, onnxsim, onnxoptimizer, onnxconverter_common\n Attempting uninstall: black\n Found existing installation: black 26.3.1\n Uninstalling black-26.3.1:\n Successfully uninstalled black-26.3.1\nSuccessfully installed black-22.3.0 docopt-0.6.2 flake8-5.0.4 isort-5.10.1 kaldi-decoder-0.2.11 kaldialign-0.9.3 kaldifst-1.7.17 kaldilm-1.15.4 mccabe-0.7.0 num2words-0.5.14 onnxconverter_common-1.16.0 onnxoptimizer-0.4.2 onnxruntime-1.24.4 onnxsim-0.6.2 pycantonese-3.4.0 pycodestyle-2.9.1 pyflakes-2.5.0 pylangacq-0.16.2 pypinyin-0.50.0 wordseg-0.0.2\nCollecting matplotlib==3.8.2 (from -r /dev/stdin (line 2))\n Downloading matplotlib-3.8.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.8 kB)\nCollecting cython==3.0.6 (from -r /dev/stdin (line 3))\n Downloading Cython-3.0.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.2 kB)\nCollecting g2p_en==2.1.0 (from -r /dev/stdin (line 4))\n Downloading g2p_en-2.1.0-py3-none-any.whl.metadata (4.5 kB)\nCollecting espnet_tts_frontend==0.0.3 (from -r /dev/stdin (line 5))\n Downloading espnet_tts_frontend-0.0.3-py3-none-any.whl.metadata (3.4 kB)\nRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (1.3.3)\nRequirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (0.12.1)\nRequirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (4.61.1)\nRequirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (1.4.9)\nCollecting numpy<2,>=1.21 (from matplotlib==3.8.2->-r /dev/stdin (line 2))\n Downloading numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.0/61.0 kB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (26.0)\nRequirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (11.3.0)\nRequirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (3.3.2)\nRequirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.12/dist-packages (from matplotlib==3.8.2->-r /dev/stdin (line 2)) (2.9.0.post0)\nRequirement already satisfied: nltk>=3.2.4 in /usr/local/lib/python3.12/dist-packages (from g2p_en==2.1.0->-r /dev/stdin (line 4)) (3.9.1)\nRequirement already satisfied: inflect>=0.3.1 in /usr/local/lib/python3.12/dist-packages (from g2p_en==2.1.0->-r /dev/stdin (line 4)) (7.5.0)\nCollecting distance>=0.1.3 (from g2p_en==2.1.0->-r /dev/stdin (line 4))\n Downloading Distance-0.1.3.tar.gz (180 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m180.3/180.3 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\nCollecting unidecode>=1.0.22 (from espnet_tts_frontend==0.0.3->-r /dev/stdin (line 5))\n Downloading Unidecode-1.4.0-py3-none-any.whl.metadata (13 kB)\nCollecting jaconv (from espnet_tts_frontend==0.0.3->-r /dev/stdin (line 5))\n Downloading jaconv-0.5.0-py3-none-any.whl.metadata (8.9 kB)\nRequirement already satisfied: pypinyin in /usr/local/lib/python3.12/dist-packages (from espnet_tts_frontend==0.0.3->-r /dev/stdin (line 5)) (0.50.0)\nRequirement already satisfied: more_itertools>=8.5.0 in /usr/local/lib/python3.12/dist-packages (from inflect>=0.3.1->g2p_en==2.1.0->-r /dev/stdin (line 4)) (10.8.0)\nRequirement already satisfied: typeguard>=4.0.1 in /usr/local/lib/python3.12/dist-packages (from inflect>=0.3.1->g2p_en==2.1.0->-r /dev/stdin (line 4)) (4.5.1)\nRequirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (8.3.1)\nRequirement already satisfied: joblib in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (1.5.3)\nRequirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (2025.11.3)\nRequirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from nltk>=3.2.4->g2p_en==2.1.0->-r /dev/stdin (line 4)) (4.67.3)\nRequirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.7->matplotlib==3.8.2->-r /dev/stdin (line 2)) (1.17.0)\nRequirement already satisfied: typing_extensions>=4.14.0 in /usr/local/lib/python3.12/dist-packages (from typeguard>=4.0.1->inflect>=0.3.1->g2p_en==2.1.0->-r /dev/stdin (line 4)) (4.15.0)\nDownloading matplotlib-3.8.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.6/11.6 MB\u001b[0m \u001b[31m84.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m0:01\u001b[0m\n\u001b[?25hDownloading Cython-3.0.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.5 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.5/3.5 MB\u001b[0m \u001b[31m34.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n\u001b[?25hDownloading g2p_en-2.1.0-py3-none-any.whl (3.1 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m104.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading espnet_tts_frontend-0.0.3-py3-none-any.whl (11 kB)\nDownloading numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.0 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.0/18.0 MB\u001b[0m \u001b[31m89.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading Unidecode-1.4.0-py3-none-any.whl (235 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m235.8/235.8 kB\u001b[0m \u001b[31m16.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading jaconv-0.5.0-py3-none-any.whl (16 kB)\nBuilding wheels for collected packages: distance\n Building wheel for distance (setup.py) ... \u001b[?25l\u001b[?25hdone\n Created wheel for distance: filename=Distance-0.1.3-py3-none-any.whl size=16256 sha256=cfcfcbfb03abe342eca6b91852a0cc02c233aee0f724af9102afc2f6847c5bc7\n Stored in directory: /root/.cache/pip/wheels/24/a8/58/407063d8e5c1d4dd6594c99d12baa0108570b56a92325587dd\nSuccessfully built distance\nInstalling collected packages: jaconv, distance, unidecode, numpy, cython, matplotlib, g2p_en, espnet_tts_frontend\n Attempting uninstall: numpy\n Found existing installation: numpy 2.0.2\n Uninstalling numpy-2.0.2:\n Successfully uninstalled numpy-2.0.2\n Attempting uninstall: cython\n Found existing installation: Cython 3.0.12\n Uninstalling Cython-3.0.12:\n Successfully uninstalled Cython-3.0.12\n Attempting uninstall: matplotlib\n Found existing installation: matplotlib 3.10.0\n Uninstalling matplotlib-3.10.0:\n Successfully uninstalled matplotlib-3.10.0\n\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\nbigframes 2.35.0 requires google-cloud-bigquery-storage<3.0.0,>=2.30.0, which is not installed.\nkaggle-environments 1.27.3 requires numpy>=2.0, but you have numpy 1.26.4 which is incompatible.\ncesium 0.12.4 requires numpy<3.0,>=2.0, but you have numpy 1.26.4 which is incompatible.\ngoogle-colab 1.0.0 requires jupyter-server==2.14.0, but you have jupyter-server 2.12.5 which is incompatible.\ngoogle-colab 1.0.0 requires pandas==2.2.2, but you have pandas 2.3.3 which is incompatible.\ndopamine-rl 4.1.2 requires gym<=0.25.2, but you have gym 0.26.2 which is incompatible.\njaxlib 0.7.2 requires numpy>=2.0, but you have numpy 1.26.4 which is incompatible.\ncupy-cuda12x 14.0.1 requires numpy<2.6,>=2.0, but you have numpy 1.26.4 which is incompatible.\nopencv-python 4.13.0.92 requires numpy>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\nshap 0.50.0 requires numpy>=2, but you have numpy 1.26.4 which is incompatible.\njax 0.7.2 requires numpy>=2.0, but you have numpy 1.26.4 which is incompatible.\nopencv-python-headless 4.13.0.92 requires numpy>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\nrasterio 1.5.0 requires numpy>=2, but you have numpy 1.26.4 which is incompatible.\ntobler 0.13.0 requires numpy>=2.0, but you have numpy 1.26.4 which is incompatible.\nxarray-einstats 0.10.0 requires numpy>=2.0, but you have numpy 1.26.4 which is incompatible.\npytensor 2.38.0 requires numpy>=2.0, but you have numpy 1.26.4 which is incompatible.\npointpats 2.5.5 requires matplotlib>=3.9, but you have matplotlib 3.8.2 which is incompatible.\nopencv-contrib-python 4.13.0.92 requires numpy>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\u001b[0m\u001b[31m\n\u001b[0mSuccessfully installed cython-3.0.6 distance-0.1.3 espnet_tts_frontend-0.0.3 g2p_en-2.1.0 jaconv-0.5.0 matplotlib-3.8.2 numpy-1.26.4 unidecode-1.4.0\nRequirement already satisfied: numba>=0.59.0 in /usr/local/lib/python3.12/dist-packages (0.60.0)\nRequirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba>=0.59.0) (0.43.0)\nRequirement already satisfied: numpy<2.1,>=1.22 in /usr/local/lib/python3.12/dist-packages (from numba>=0.59.0) (1.26.4)\nObtaining file:///kaggle/working/icefall\n Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n Checking if build backend supports build_editable ... \u001b[?25l\u001b[?25hdone\n Getting requirements to build editable ... \u001b[?25l\u001b[?25hdone\n Preparing editable metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\nRequirement already satisfied: kaldifst>1.7.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.7.17)\nRequirement already satisfied: kaldilm in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.15.4)\nRequirement already satisfied: kaldialign in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.9.3)\nRequirement already satisfied: num2words in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.5.14)\nRequirement already satisfied: kaldi-decoder in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.2.11)\nRequirement already satisfied: sentencepiece>=0.1.96 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.2.1)\nRequirement already satisfied: pypinyin==0.50.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.50.0)\nRequirement already satisfied: tensorboard in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (2.19.0)\nRequirement already satisfied: typeguard in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (4.5.1)\nRequirement already satisfied: dill in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.4.1)\nRequirement already satisfied: onnx>=1.15.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.20.1)\nRequirement already satisfied: onnxruntime>=1.16.3 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.24.4)\nRequirement already satisfied: onnxoptimizer in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.4.2)\nRequirement already satisfied: onnxsim in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (0.6.2)\nRequirement already satisfied: onnxconverter_common in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (1.16.0)\nRequirement already satisfied: black==22.3.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (22.3.0)\nRequirement already satisfied: isort==5.10.1 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (5.10.1)\nRequirement already satisfied: flake8==5.0.4 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (5.0.4)\nRequirement already satisfied: pycantonese==3.4.0 in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (3.4.0)\nRequirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from icefall==1.0) (26.0)\nRequirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (8.3.1)\nRequirement already satisfied: platformdirs>=2 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (4.9.2)\nRequirement already satisfied: pathspec>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (1.0.4)\nRequirement already satisfied: mypy-extensions>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from black==22.3.0->icefall==1.0) (1.1.0)\nRequirement already satisfied: mccabe<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (0.7.0)\nRequirement already satisfied: pycodestyle<2.10.0,>=2.9.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (2.9.1)\nRequirement already satisfied: pyflakes<2.6.0,>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from flake8==5.0.4->icefall==1.0) (2.5.0)\nRequirement already satisfied: pylangacq<0.17.0,>=0.16.0 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->icefall==1.0) (0.16.2)\nRequirement already satisfied: wordseg==0.0.2 in /usr/local/lib/python3.12/dist-packages (from pycantonese==3.4.0->icefall==1.0) (0.0.2)\nRequirement already satisfied: numpy>=1.23.2 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (1.26.4)\nRequirement already satisfied: protobuf>=4.25.1 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (5.29.5)\nRequirement already satisfied: typing_extensions>=4.7.1 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (4.15.0)\nRequirement already satisfied: ml_dtypes>=0.5.0 in /usr/local/lib/python3.12/dist-packages (from onnx>=1.15.0->icefall==1.0) (0.5.4)\nRequirement already satisfied: flatbuffers in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->icefall==1.0) (25.12.19)\nRequirement already satisfied: sympy in /usr/local/lib/python3.12/dist-packages (from onnxruntime>=1.16.3->icefall==1.0) (1.14.0)\nRequirement already satisfied: docopt>=0.6.2 in /usr/local/lib/python3.12/dist-packages (from num2words->icefall==1.0) (0.6.2)\nRequirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from onnxsim->icefall==1.0) (13.9.4)\nRequirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.4.0)\nRequirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.78.1)\nRequirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (3.10.2)\nRequirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (75.2.0)\nRequirement already satisfied: six>1.9 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (1.17.0)\nRequirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (0.7.2)\nRequirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from tensorboard->icefall==1.0) (3.1.6)\nRequirement already satisfied: python-dateutil<=3.0.0,>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.9.0.post0)\nRequirement already satisfied: requests<=3.0.0,>=2.18.0 in /usr/local/lib/python3.12/dist-packages (from pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.32.4)\nRequirement already satisfied: tabulate<=0.9.0,>=0.8.9 in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (0.9.0)\nRequirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.12/dist-packages (from werkzeug>=1.0.1->tensorboard->icefall==1.0) (3.0.3)\nRequirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->icefall==1.0) (4.0.0)\nRequirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->onnxsim->icefall==1.0) (2.19.2)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy->onnxruntime>=1.16.3->icefall==1.0) (1.3.0)\nRequirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->onnxsim->icefall==1.0) (0.1.2)\nRequirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (3.4.4)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (3.11)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2.5.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<=3.0.0,>=2.18.0->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (2026.1.4)\nRequirement already satisfied: wcwidth in /usr/local/lib/python3.12/dist-packages (from tabulate[widechars]<=0.9.0,>=0.8.9->pylangacq<0.17.0,>=0.16.0->pycantonese==3.4.0->icefall==1.0) (0.6.0)\nBuilding wheels for collected packages: icefall\n Building editable for icefall (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n Created wheel for icefall: filename=icefall-1.0-0.editable-py3-none-any.whl size=7298 sha256=78814702c840e8fffb04e47e141e95ad7f9fc34004e617ecdc927e34bfbe0ad8\n Stored in directory: /tmp/pip-ephem-wheel-cache-sdjpxxq4/wheels/15/7d/60/a461439407a382249acfd8d18f7237475e164801218e112983\nSuccessfully built icefall\nInstalling collected packages: icefall\nSuccessfully installed icefall-1.0\nLooking in links: https://k2-fsa.github.io/icefall/piper_phonemize.html\nCollecting piper_phonemize\n Downloading https://github.com/csukuangfj/piper-phonemize/releases/download/2025.06.23/piper_phonemize-1.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.4 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.4/9.4 MB\u001b[0m \u001b[31m65.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hInstalling collected packages: piper_phonemize\nSuccessfully installed piper_phonemize-1.3.0\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"from huggingface_hub import hf_hub_download\nimport os, shutil\n\nMODEL_ID = \"zrjin/icefall-tts-vctk-vits-2024-03-18\"\nBASE_DIR = \"/kaggle/working/icefall/egs/vctk/TTS\"\n\nos.makedirs(f\"{BASE_DIR}/vits/exp\", exist_ok=True)\nos.makedirs(f\"{BASE_DIR}/data\", exist_ok=True)\n\n# Download checkpoint (~1.08 GB).\n# hf_hub_download preserves the repo path → saves to BASE_DIR/exp/epoch-1000.pt\n# But infer.py / train.py expect it at BASE_DIR/vits/exp/epoch-1000.pt\n# So: download first, then move to the correct location.\nhf_hub_download(repo_id=MODEL_ID, filename=\"exp/epoch-1000.pt\", local_dir=BASE_DIR)\nshutil.copy2(f\"{BASE_DIR}/exp/epoch-1000.pt\", f\"{BASE_DIR}/vits/exp/epoch-1000.pt\")\n\n# Phoneme token map (required by both train.py and infer.py)\nhf_hub_download(repo_id=MODEL_ID, filename=\"data/tokens.txt\", local_dir=BASE_DIR)\n\n# Speaker ID list (required by infer.py to build speaker → int map)\nhf_hub_download(repo_id=MODEL_ID, filename=\"data/speakers.txt\", local_dir=BASE_DIR)\n\nprint(\"Ready.\")\nprint(f\" Model : {BASE_DIR}/vits/exp/epoch-1000.pt\")\nprint(f\" Tokens : {BASE_DIR}/data/tokens.txt\")\nprint(f\" Speakers: {BASE_DIR}/data/speakers.txt\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:54:08.725687Z","iopub.execute_input":"2026-04-09T02:54:08.725954Z","iopub.status.idle":"2026-04-09T02:54:18.340902Z","shell.execute_reply.started":"2026-04-09T02:54:08.725924Z","shell.execute_reply":"2026-04-09T02:54:18.340103Z"}},"outputs":[{"name":"stderr","text":"Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"exp/epoch-1000.pt: 0%| | 0.00/1.08G [00:00k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.24.3)\nRequirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (4.15.0)\nRequirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (75.2.0)\nRequirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.14.0)\nRequirement already satisfied: networkx>=2.5.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.6.1)\nRequirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.1.6)\nRequirement already satisfied: fsspec>=0.8.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2026.2.0)\nRequirement already satisfied: cuda-bindings==12.9.4 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.9.4)\nRequirement already satisfied: nvidia-cuda-nvrtc-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.93)\nRequirement already satisfied: nvidia-cuda-runtime-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-cuda-cupti-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (9.10.2.21)\nRequirement already satisfied: nvidia-cublas-cu12==12.8.4.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.4.1)\nRequirement already satisfied: nvidia-cufft-cu12==11.3.3.83 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (11.3.3.83)\nRequirement already satisfied: nvidia-curand-cu12==10.3.9.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (10.3.9.90)\nRequirement already satisfied: nvidia-cusolver-cu12==11.7.3.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (11.7.3.90)\nRequirement already satisfied: nvidia-cusparse-cu12==12.5.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.5.8.93)\nRequirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (0.7.1)\nRequirement already satisfied: nvidia-nccl-cu12==2.27.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (2.27.5)\nRequirement already satisfied: nvidia-nvshmem-cu12==3.4.5 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.4.5)\nRequirement already satisfied: nvidia-nvtx-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.90)\nRequirement already satisfied: nvidia-nvjitlink-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (12.8.93)\nRequirement already satisfied: nvidia-cufile-cu12==1.13.1.3 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.13.1.3)\nRequirement already satisfied: triton==3.6.0 in /usr/local/lib/python3.12/dist-packages (from torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.6.0)\nRequirement already satisfied: cuda-pathfinder~=1.1 in /usr/local/lib/python3.12/dist-packages (from cuda-bindings==12.9.4->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.3.5)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (1.3.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch==2.10.0->k2==1.24.4.dev20260306+cuda12.8.torch2.10.0) (3.0.3)\nInstalling collected packages: k2\nSuccessfully installed k2-1.24.4.dev20260306+cuda12.8.torch2.10.0\n","output_type":"stream"}],"execution_count":6},{"cell_type":"code","source":"%cd /kaggle/working/icefall/egs/vctk/TTS\n\n# Generate audio from the pretrained model\n# Output is saved to: vits/exp/infer/epoch-1000/wav/\n!CUDA_VISIBLE_DEVICES=\"0\" python vits/infer.py \\\n --epoch 1000 \\\n --exp-dir vits/exp \\\n --tokens data/tokens.txt \\\n --max-duration 500","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-09T02:56:38.176388Z","iopub.execute_input":"2026-04-09T02:56:38.177210Z","iopub.status.idle":"2026-04-09T02:57:17.644961Z","shell.execute_reply.started":"2026-04-09T02:56:38.177177Z","shell.execute_reply":"2026-04-09T02:57:17.644194Z"}},"outputs":[{"name":"stdout","text":"/kaggle/working/icefall/egs/vctk/TTS\n2026-04-09 02:56:47.073483: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\nWARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nE0000 00:00:1775703407.551010 753 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\nE0000 00:00:1775703407.674997 753 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\nW0000 00:00:1775703408.812968 753 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\nW0000 00:00:1775703408.813024 753 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\nW0000 00:00:1775703408.813031 753 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\nW0000 00:00:1775703408.813036 753 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n/kaggle/working/icefall/icefall/utils.py:1664: SyntaxWarning: invalid escape sequence '\\d'\n \\delta = \\frac{\\Vert\\theta - \\theta_{new}\\Vert^2}{\\Vert\\theta\\Vert^2}\n2026-04-09 02:57:10,687 INFO [infer.py:212] Infer started\n2026-04-09 02:57:10,688 INFO [tts_datamodule.py:338] About to get speakers\n2026-04-09 02:57:10,688 INFO [infer.py:228] Device: cuda:0\n2026-04-09 02:57:10,688 INFO [infer.py:229] {\n \"batch_idx_train\": -1,\n \"best_train_epoch\": -1,\n \"best_train_loss\": Infinity,\n \"best_valid_epoch\": -1,\n \"best_valid_loss\": Infinity,\n \"blank_id\": 0,\n \"bucketing_sampler\": true,\n \"drop_last\": true,\n \"env_info\": {\n \"IP address\": \"172.19.2.2\",\n \"hostname\": \"84b6d71676cc\",\n \"icefall-git-branch\": \"master\",\n \"icefall-git-date\": \"Wed Mar 25 05:01:22 2026\",\n \"icefall-git-sha1\": \"e9f4eb08-clean\",\n \"icefall-path\": \"/kaggle/working/icefall\",\n \"k2-build-type\": \"Release\",\n \"k2-git-date\": \"Fri Mar 6 06:05:26 2026\",\n \"k2-git-sha1\": \"bd61709fb9defe371bfdbc7c5a9dd88d902fc374\",\n \"k2-path\": \"/usr/local/lib/python3.12/dist-packages/k2/__init__.py\",\n \"k2-version\": \"1.24.4\",\n \"k2-with-cuda\": true,\n \"lhotse-path\": \"/usr/local/lib/python3.12/dist-packages/lhotse/__init__.py\",\n \"lhotse-version\": \"1.32.2\",\n \"python-version\": \"3.12\",\n \"torch-cuda-available\": true,\n \"torch-cuda-version\": \"12.8\",\n \"torch-version\": \"2.10.0+cu128\"\n },\n \"epoch\": 1000,\n \"exp_dir\": \"vits/exp\",\n \"feature_dim\": 513,\n \"frame_length\": 1024,\n \"frame_shift\": 256,\n \"input_strategy\": \"PrecomputedFeatures\",\n \"lambda_adv\": 1.0,\n \"lambda_dur\": 1.0,\n \"lambda_feat_match\": 2.0,\n \"lambda_kl\": 1.0,\n \"lambda_mel\": 45.0,\n \"log_interval\": 50,\n \"manifest_dir\": \"data/spectrogram\",\n \"max_duration\": 500,\n \"n_mels\": 80,\n \"num_buckets\": 30,\n \"num_spks\": 108,\n \"num_workers\": 8,\n \"on_the_fly_feats\": false,\n \"res_dir\": \"vits/exp/infer/epoch-1000\",\n \"return_cuts\": false,\n \"sampling_rate\": 22050,\n \"save_wav_dir\": \"vits/exp/infer/epoch-1000/wav\",\n \"shuffle\": true,\n \"speakers\": \"data/speakers.txt\",\n \"suffix\": \"epoch-1000\",\n \"tokens\": \"data/tokens.txt\",\n \"valid_interval\": 200,\n \"vocab_size\": 159\n}\n2026-04-09 02:57:10,688 INFO [infer.py:231] About to create model\n/usr/local/lib/python3.12/dist-packages/torch/nn/utils/weight_norm.py:144: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.\n WeightNorm.apply(module, name, dim)\n/kaggle/working/icefall/egs/vctk/TTS/vits/monotonic_align/__init__.py:25: UserWarning: Cython version is not available. Fallback to 'EXPERIMETAL' numba version. If you want to use the cython version, please build it as follows: `cd espnet2/gan_tts/vits/monotonic_align; python setup.py build_ext --inplace`\n warnings.warn(\n2026-04-09 02:57:14,011 INFO [checkpoint.py:111] Loading checkpoint from vits/exp/epoch-1000.pt\n2026-04-09 02:57:15,395 INFO [infer.py:240] Number of parameters in generator: 39004210\n2026-04-09 02:57:15,395 INFO [infer.py:242] Number of parameters in discriminator: 50974956\n2026-04-09 02:57:15,396 INFO [infer.py:243] Total number of parameters: 89979166\n2026-04-09 02:57:15,396 INFO [tts_datamodule.py:333] About to get test cuts\nTraceback (most recent call last):\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/infer.py\", line 273, in \n main()\n File \"/usr/local/lib/python3.12/dist-packages/torch/utils/_contextlib.py\", line 124, in decorate_context\n return func(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/infer.py\", line 245, in main\n test_cuts = vctk.test_cuts()\n ^^^^^^^^^^^^^^^^\n File \"/kaggle/working/icefall/egs/vctk/TTS/vits/tts_datamodule.py\", line 334, in test_cuts\n return load_manifest_lazy(self.args.manifest_dir / \"vctk_cuts_test.jsonl.gz\")\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/serialization.py\", line 475, in load_manifest_lazy\n first = next(raw_data)\n ^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/serialization.py\", line 146, in load_jsonl\n with open_best(path, \"r\") as f:\n ^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/serialization.py\", line 48, in open_best\n return get_current_io_backend().open(path, mode)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/serialization.py\", line 951, in open\n return b.open(identifier, mode)\n ^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/serialization.py\", line 762, in open\n return gzip_open_robust(identifier, mode)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.12/dist-packages/lhotse/workarounds.py\", line 108, in gzip_open_robust\n binary_file = AltGzipFile(filename, gz_mode, compresslevel)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/lib/python3.12/gzip.py\", line 201, in __init__\n fileobj = self.myfileobj = builtins.open(filename, mode or 'rb')\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nFileNotFoundError: [Errno 2] No such file or directory: 'data/spectrogram/vctk_cuts_test.jsonl.gz'\n","output_type":"stream"}],"execution_count":9},{"cell_type":"code","source":"import os\nfrom IPython.display import Audio, display\n\nwav_dir = \"/kaggle/working/icefall/egs/vctk/TTS/vits/exp/infer/epoch-1000/wav\"\nwav_files = sorted(os.listdir(wav_dir))\n\n# Play the first 3 generated audio files\nfor f in wav_files[:3]:\n print(f)\n display(Audio(os.path.join(wav_dir, f)))","metadata":{"trusted":true},"outputs":[],"execution_count":null}]} \ No newline at end of file