Convert to package and add libritts data prep script

jishengpeng / WavTokenizer

SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

MIT License

658 stars 37 forks source link

Convert to package and add libritts data prep script #9

Closed saveriyo closed 2 weeks ago

saveriyo commented 2 weeks ago

Adds pyproject.toml to be able to run pip install -e . and use the wavtokenizer module
Adds gitignore
Adds prepare_libritts.py to download, extract, and prep libritts for training

saveriyo commented 2 weeks ago

@jishengpeng Thanks for making WavTokenizer! I wanted to try it out in Speechbrain, and the best way I could find was converting to a package. Please let me know if you have feedback or changes / feel free to decline if this doesn't make sense for now or with HF integrations

saveriyo commented 2 weeks ago

I'm attempting to update to Pytorch Lightning 2.0+ and then will open a PR