yl4579/StyleTTS2

Awesome in english but no support for other languages - please add an example for another language (german, italian, french etc)

Open

#41 opened on Nov 20, 2023

View on GitHub
 (89 comments) (15 reactions) (0 assignees)Python (210 forks)batch import
help wanted

Repository metrics

Stars
 (3,429 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

The readme makes it sound very simple: "Replace bert with xphonebert" Looking a bit closer looks like it's quite a feat to make StyleTTS2 talk in non-english languages (https://github.com/yl4579/StyleTTS2/issues/28)

StyleTTS2 looks like the best approach we have right now, but only english is a killer for many as it means any app will be limited to english without prospect for other users in sight.

Some help to get this going in foreign languages would be awesome.

It appears we need to change inference code and re-train text and phonetics. Any demo/guide would be great

Alternatively re-training the current PL-Bert for other languages, though that needs a corpus and I've no idea on the cost ? (https://github.com/yl4579/PL-BERT)

Contributor guide

Research direction
Investigate how to adapt StyleTTS2 for other languages by examining the current English pipeline, phoneme conversion (e.g., using g2p for the target language), and fine tuning PL BERT with multilingual phoneme embeddings. Look at existing issues and discussions for pointers, and consider creating a sample guide for one language (e.g., German) as a starting point.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60