Cornelius Justin Satryo Hadi comments

Results 7 comments of


                                            Cornelius Justin Satryo Hadi

Strange Loss Behavior During Stage Two Training - Not Decreasing after Diff Epoch

hi @ethan-digi have you solved this issue?

Add a new language but the result is a meaningless audio.

hi @MiXaiLL76 did you found a way to train new languages correctly? thanks

Other languages

hi @aluminumbox , do you think it's better to train cosyvoice from scratch or just finetune the CosyVoice-300M base model if I want to train on new language? Also, should...

@aluminumbox should we also change the `language` parameter in the get_tokenizer config? ``` get_tokenizer: !name:whisper.tokenizer.get_tokenizer # change to !name:cosyvoice.tokenizer.tokenizer.get_tokenizer if you want to train with CosyVoice-300M-25Hz recipe multilingual: True num_languages:...

How can I add new language?

@aluminumbox is 800-900 hours audio enough for training new languages? or should I train it from scratch?

How can I add new language?

> no need to train from scratch, I think at least 5k+ hour is suitable to cover a new language should I finetune the llm and the flow, or just...

Hi, I'm currently trying to use an updated wespeaker voice model like the one shown in the picture, but when I follow the file pyannote/audio/models/embedding/wespeaker/convert.py I can't adapt it, it shows the following error, how do I change ？

Hi @clement-pages are there any alternative to use SimAMResNet for pyannote speaker diarization embedding model?