Yoach Lacombe

Results 53 comments of Yoach Lacombe

It's been a long ride, but merging now! Thanks again for the great work and your patience !

Hey there, I don't know about the official implementation (cc @cndn and @elbayadm) but it seems to work with `transformers` when I tried to reproduce your errors: ```python from transformers...

Hey @hscspring, thanks for opening the issue, this is something that needs to be improved but I actually used the same tokenizer but with two different sets of parameters during...

Hi @Zengyi-Qin, I'm Yoach, ML Engineer at Hugging Face, nice to meet you! Congrats on the release ! The models are definitely of great quality! I'd be happy to help...

I've updated an example of model card [here](https://huggingface.co/myshell-ai/MeloTTS-Korean) (for Korean), don't hesitate to modify it and adapt it for the other languages

Hey @anioji, thanks for opening this issue, have you tried to follow the [README](https://github.com/huggingface/dataspeech) from dataspeech ? If not, please let me know where you're facing issues! In any case,...

Hey @anioji, thanks for bringing more details! As said, I'm working on making this a bit clearer. In the meantime, here are a few recommendations for your particular use-case: ->...

Hey @anioji, I've also updated the README to facilitate preparing your datasets for fine-tuning: https://github.com/huggingface/dataspeech?tab=readme-ov-file#annotating-datasets-to-fine-tune-parler-tts

I've released this repository to allow VITS/MMS finetuning with transformer compatibility: https://github.com/ylacombe/finetune-hf-vits Feel free to check it :hugs:

Hi @borboto , @mkosecki's [comment](https://github.com/suno-ai/bark/issues/402#issuecomment-1672725122) is right. This is not an error but actually only a warning because the forward pass of `transformers` models usually expect an `attention_mask`. This is...