open-mmlab / Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
https://openhlt.github.io/amphion/
MIT License
4.45k stars 379 forks source link

Refine the multilingual front-end processing module #137

Closed lmxue closed 6 months ago

lmxue commented 6 months ago

✨ Description

We support espeak to extract IPA (International Phonetic Alphabet), which supports 100 languages, just shown in https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md.

To highlight this support, this PR add comments for espeak tool with support of 100 languages to provide more helpful information. Also, Refine the multilingual front-end processing module, i.e., G2PModule, by passing the parameter of language to EspeakBackend.

🚧 Related Issues

112

👨‍💻 Changes Proposed

🧑‍🤝‍🧑 Who Can Review?

@RMSnow

🛠 TODO

None

✅ Checklist