Jakub Piotr Cłapa
Jakub Piotr Cłapa
Hi, thanks a lot for the invite! :) A Huggingface spaces demo would probably be more accessible than Google Collab. Having a more performant GPU available for people to play...
Hey, @Josephrp started working on this one just yesterday. Maybe you can reach out to him on the LAION Discord (link in the README, his username: Tonic) and ask if...
Both these features should be possible if we implement #52
Yes, you're right. This would give you the most control over the style and voice of each speaker. One could probably find or train a traditional NLP preprocessing model to...
These is also #58 , which would also be useful. Maybe this can be the umbrella task. :)
Not right now but we are looking into adding such capability for the next release of the model (in a month or two).
Hey, great question. Does Whisper work for Mandarin? I found https://github.com/openai/whisper/discussions/25 but it's seem inconclusive to me? I'll test today how Whisper semantic tokens from an English only model behave...
We plan to train another quantized semantic token model based on the multilingual Whisper medium model soon. Medium seems like a good quality/speed tradeoff that should improve the quality a...
The demos in the readme are all trained on around 1000hours so we may can get something usable with this amount of data (and multiple languages may benefit from each...
Hey, we now have an English + Polish model so the architecture is validated for other languages. Right now it looks like we need a few hundred hours of speech...