naozumi520 / bert-vits2-cantonese-yue

vits2 backbone with multilingual-bert, modified to support Cantonese

Hello there 👋

Basic info 📝

Name: Naozumi
Job: Student
Location: HK
Hobby: Coding, explore fun projects.

---

---

Social links 🤝

Operating systems 💻

Softwares 🛠

Skills 🚀

Top Langs

Highlighted projects 🌟

bert-vits2-cantonese-yue's Issues

text_normalize() remove all alphabet characters

Bert-VITS2-Cantonese-Yue/text/chinese.py

Line 109 in 36790b0

text = replace_punctuation(text)

Is it intended?

Transcription

This is a discussion thread rather than a issue. I put it here since there is no discussion space in this repo. Any help is much appreciated!

1. I found that the whipser asr is not accurate enough, even for large v3. Is there better model for transcription? I've tried funasr, the result seems to be better, but still need lots of manually fix.
2. Do we need punctuation in the training .list file?

请教如何训练一个四川话模型

如题，请问您粤语底模是如何训练出来的呢，用了多少小时训练集呢。我想训练一个四川话的底模，可以分享一些思路吗

Audio length

Hi, thanks for your effort!
In your expriments, how long doest it take for audio files to train a decent model?
In this issue, you said you've trained with 9~11 hours of data, is this the model hosted in the huggingface page? I've asked my friend who is a native cantonese speaker, he said the output quality is not so good, is there room for improvement if more data is used for training? or is there flaw in the text frontend or base model which limited the quality?
Many thanks!