Automatic speech recognition for people with dysarthria
Model is hosted on Hugging Face: https://huggingface.co/jmaczan/wav2vec2-large-xls-r-300m-dysarthria
# clone project
git clone https://github.com/jmaczan/asr-dysarthria
cd asr-dysarthria
# [OPTIONAL] create conda environment
conda create -n asr-dysarthria python=3.9
conda activate asr-dysarthria
# install pytorch according to instructions
# https://pytorch.org/get-started/
# install requirements
pip install -r requirements.txt
# clone project
git clone https://github.com/jmaczan/asr-dysarthria
cd asr-dysarthria
# create conda environment and install dependencies
conda env create -f environment.yaml -n asr-dysarthria
# activate conda environment
conda activate asr-dysarthria
Train model with default configuration
# train on CPU
python src/train.py trainer=cpu
# train on GPU
python src/train.py trainer=gpu
Train model with chosen experiment configuration from configs/experiment/
python src/train.py experiment=experiment_name.yaml
You can override any parameter from command line like this
python src/train.py trainer.max_epochs=20 data.batch_size=64
Run python oldies/src/torgo_dataset_builder.py
http://www.cs.toronto.edu/~complingweb/data/TORGO/torgo.html
Dataset is hosted on Hugging Face: https://huggingface.co/datasets/jmaczan/TORGO
- How to do audio data augmentation for TORGO dataset?
- How to obtain Nemours database of dysarthric speech? https://ieeexplore.ieee.org/document/608020
https://ar5iv.labs.arxiv.org/html/2204.00770 (https://arxiv.org/abs/2204.00770)
https://www.isca-speech.org/archive/pdfs/interspeech_2022/baskar22b_interspeech.pdf
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10225595
https://www.sciencedirect.com/science/article/pii/S2405959521000874
https://www.isca-speech.org/archive/pdfs/interspeech_2021/green21_interspeech.pdf
https://arxiv.org/pdf/2006.11477.pdf
https://arxiv.org/pdf/2211.00089.pdf
https://www.sciencedirect.com/science/article/abs/pii/S0957417423002981
https://huggingface.co/blog/fine-tune-wav2vec2-english
http://www.cs.toronto.edu/~complingweb/data/TORGO/torgo.html
https://huggingface.co/datasets/jmaczan/TORGO
https://huggingface.co/datasets/jmaczan/TORGO-very-small
https://ai.meta.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/
https://pytorch.org/audio/stable/tutorials/speech_recognition_pipeline_tutorial.html
https://huggingface.co/docs/datasets/v2.16.1/audio_dataset
https://ai.meta.com/blog/self-supervision-and-building-more-robust-speech-recognition-systems/
MIT License
Made in Kaszëbë, Poland 🇵🇱 by Jędrzej Paweł Maczan, on the shoulders of giants in 2024