This Repository contains the code for language identification from speech utterance. This repository uses s3prl library to load various upstream models like wav2vec2, CPC, TERA etc.
Use the package manager pip to install the required packages for preparing the dataset, training and testing the model.
pip install -r requirements.txt
Update the config.py file to update the upstream model, batch_size, gpus, lr, etc and change the preferred logger in train.py files
./run.sh
./run_test.sh
- [1] S3prl: The self-supervised speech pre-training and representation learning toolkit. AT Liu, Y Shu-wen