Ray

Thanks for your great work on WhisperSpeech! It is very interesting to extract semantic tokens from the Whisper encoder, and use semantic tokens to generate acoustic tokens. I am a...

Audio format in dataset files

2

Thanks for you great work on implementing FACodec! I found the data file in https://github.com/Plachtaa/FAcodec/blob/master/data/val.txt has some labels, like speaker id, phonemes. How can I get these labels? Will these...

### Describe the bug When fine-tuning XTTS_v2 on LJSpeech following the script (recipes/ljspeech/xtts_v2/train_gpt_xtts.py), the loss is always NaN! So terrible. I try to reduce the learning rate, change the batch...

Where is the UniCATS testset-B?

1

I found that X-LANCE's work [1, 2] also takes UniCATS testset-B as the test set. Maybe it is a good choice to open source the UniCATS testset-B for reproduction. [1]...