egs/vctk/TTS: Add --local-data-dir option to skip VCTK download

.gitignore

@@ -36,3 +36,4 @@ node_modules
 .DS_Store
 *.fst
 *.arpa
+.venv/

egs/vctk/TTS/README.md

@@ -1,11 +1,34 @@
 # 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. 
+Follow this: https://k2-fsa.github.io/icefall/recipes/TTS/vctk/vits.html
+
+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).
 
 The above information is from the [CSTR VCTK website](https://datashare.ed.ac.uk/handle/10283/3443).
 
+# 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
 
 This recipe provides a VITS model trained on the VCTK dataset.
@@ -22,7 +45,7 @@ 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
 ```
 

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