Chinese is a unique language. When I want to train and process with other languages, such as Vietnamese, Spanish, or Lao, do I need to change the data processing method? Specifically, the function ...
@vu-the-dung, oh no problem. But i think the data needs additional periods and commas because the model will learn to pause accordingly. Also, capital letters will help the model learn to emphasize...
@vu-the-dung I think the data needs additional periods and commas because the model will learn to pause accordingly. Also, capital letters will help the model learn to emphasize tone in the audio. ...
@PhamDangNguyen my dataset already have normalized text, even without punctuation. And after some test inferences with punctuation in gen_text, I'm feeling like the model have forgotten to pause at...
I only tested with Vietnamese. I saw that after adding missing Vietnamese characters to vocab.txt, when calling convert_char_to_pinyin with a sentence in Vietnamese, the returned char array often h...
After rolling back this commit, it can run, but the generated file is a current sound. [46d391a](url) [](https://github.com/SWivid/F5-TTS/commit/46d391a8766d8eabb967b326ccb473bc2d8b9a6c)
Chinese is a unique language. When I want to train and process with other languages, such as Vietnamese, Spanish, or Lao, do I need to change the data processing method? Specifically, the function ...
> I had a similar issue and resolved it by installing a different version of the package.
>
> Replace this:
>
> ```
> pip install torch==2.3.0+cu118 torchaudio==2.3.0+cu118 --extra-index-url...
I had a similar issue and resolved it by installing a different version of the package.
Replace this:
```
pip install torch==2.3.0+cu118 torchaudio==2.3.0+cu118 --extra-index-url https://dow...