open source version

.gitignore

@@ -0,0 +1,131 @@
+*.pkl
+*DS_Store
+data/
+experiments/
+configs/
+._data
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

README.md

@@ -0,0 +1,73 @@
+# Capitalisation And PuncTuatION (CAPTION)
+> PT2020 Transcription project.
+
+In this repository, we explore different strategies for automatic transcription enrichment for ASR data which includes tasks such as automatic capitalization (truecasing) and punctuation recovery.
+
+## Model architecture:
+
+![base_model](https://i.ibb.co/sm3P2Bq/Screenshot-2020-04-14-at-16-19-10.png)
+
+### Available Encoders:
+- [BERT](https://arxiv.org/abs/1810.04805)
+- [RoBERTa](https://arxiv.org/abs/1907.11692)
+- [XLM-RoBERTa](https://arxiv.org/pdf/1911.02116.pdf)
+
+## Requirements:
+
+This project uses Python >3.6
+
+Create a virtual env with (outside the project folder):
+
+```bash
+virtualenv -p python3.6 caption-env
+```
+
+Activate venv:
+```bash
+source caption-env/bin/activate
+```
+
+Finally, run:
+```bash
+python setup.py install
+```
+
+If you wish to make changes into the code run:
+```bash
+pip install -r requirements.txt
+pip install -e .
+```
+
+## Getting Started:
+
+### Train:
+```bash
+python caption train -f {your_config_file}.yaml
+```
+
+### Testing:
+```bash
+python caption test \
+    --checkpoint=some/path/to/your/checkpoint.ckpt \
+    --test_csv=path/to/your/testset.csv
+```
+
+### Tensorboard:
+
+Launch tensorboard with:
+```bash
+tensorboard --logdir="experiments/lightning_logs/"
+```
+
+If you are running experiments in a remote server you can forward your localhost to the server localhost..
+
+### How to run the tests:
+In order to run the toolkit tests you must run the following command:
+
+```bash
+cd tests
+python -m unittest
+```
+
+### Code Style:
+To make sure all the code follows the same style we use [Black](https://github.com/psf/black).

caption/__main__.py

@@ -0,0 +1,86 @@
+# -*- coding: utf-8 -*-
+import logging
+from data_loader import add_data_args
+
+from models import add_model_args, build_model
+from optimizers import add_optimizer_args
+from schedulers import add_scheduler_args
+from test_tube import HyperOptArgumentParser
+from testing import run_testing, setup_testing
+from torchnlp.random import set_seed
+from training import add_trainer_specific_args, setup_training
+from utils import get_main_args_from_yaml, load_yaml_args
+
+log = logging.getLogger("Shell")
+logging.basicConfig(level=logging.INFO)
+
+
+def run_training_pipeline(parser):
+    parser.add_argument(
+        "-f", "--config", default=False, type=str, help="Path to a YAML config file."
+    )
+    parser.add_argument(
+        "--optimizer",
+        default=False,
+        type=str,
+        help="Optimizer to be used during training.",
+    )
+    parser.add_argument(
+        "--scheduler",
+        default=False,
+        type=str,
+        help="LR scheduler to be used during training.",
+    )
+    parser.add_argument(
+        "--model",
+        default=False,
+        type=str,
+        help="The estimator architecture we we wish to use.",
+    )
+    args, _ = parser.parse_known_args()
+
+    if not args.optimizer and not args.scheduler and not args.model:
+        optimizer, scheduler, model = get_main_args_from_yaml(args)
+    else:
+        optimizer = args.optimizer
+        scheduler = args.scheduler
+        model = args.model
+
+    parser = add_optimizer_args(parser, optimizer)
+    parser = add_scheduler_args(parser, scheduler)
+    parser = add_model_args(parser, model)
+    parser = add_trainer_specific_args(parser)
+    hparams = load_yaml_args(parser=parser, log=log)
+
+    set_seed(hparams.seed)
+    model = build_model(hparams)
+    trainer = setup_training(hparams)
+
+    if hparams.load_weights:
+        model.load_weights(hparams.load_weights)
+
+    log.info(f"{model.__class__.__name__} train starting:")
+    trainer.fit(model)
+
+
+def run_testing_pipeline(parser):
+    parser = add_data_args(parser)
+    parser.add_argument(
+        "--checkpoint", default=None, help="Checkpoint file path.",
+    )
+    hparams = parser.parse_args()
+    run_testing(hparams)
+
+
+if __name__ == "__main__":
+    parser = HyperOptArgumentParser(
+        strategy="random_search", description="CAPTION project", add_help=True
+    )
+    parser.add_argument(
+        "pipeline", choices=["train", "test"], help="train a model or test.",
+    )
+    args, _ = parser.parse_known_args()
+    if args.pipeline == "test":
+        run_testing_pipeline(parser)
+    else:
+        run_training_pipeline(parser)