Speech to Phoneme, Bandwidth Extension and Speaker Verification using the Vibravox dataset.
- 📝: The paper related to this project is available on arXiv on this link.
- 🤗: The dataset used in this project is hosted by Hugging Face. You can access it here.
- 🌐: For more information about the project, visit our project page.
- 🏆: Explore Leaderboards on Papers With Code.
pip install -r requirements.txt
- Train EBEN for Bandwidth Extension
python run.py lightning_datamodule=bwe lightning_datamodule.sensor=throat_microphone lightning_module=eben ++trainer.check_val_every_n_epoch=15 ++trainer.max_epochs=500
- Train wav2vec2 for Speech to Phoneme
python run.py lightning_datamodule=stp lightning_datamodule.sensor=headset_microphone lightning_module=wav2vec2_for_stp lightning_module.optimizer.lr=1e-5 ++trainer.max_epochs=10
- Test ECAPA2 for Speaker Verification
python run.py lightning_datamodule=spkv lightning_module=ecapa2 logging=csv ++trainer.limit_train_batches=0 ++trainer.limit_val_batches=0