Skip to content
This repository has been archived by the owner on Jan 30, 2024. It is now read-only.

Implement Massively Multilingual Speech - Meta's Open Source model with less than half of Whispers error rate #48

Open
menelic opened this issue May 23, 2023 · 0 comments
Open

Implement Massively Multilingual Speech - Meta's Open Source model with less than half of Whispers error rate #48

menelic opened this issue May 23, 2023 · 0 comments
Assignees
@hayabhay
Labels
enhancement New feature or request

Comments

@menelic
Copy link

menelic commented May 23, 2023

Please consider implementing Meta's MMS with speech recognition and generation support for over 1000 languages at a drastically reduced error rate compared to Whisper:

image

https://github.com/facebookresearch/fairseq/tree/main/examples/mms

https://ai.facebook.com/blog/multilingual-model-speech-recognition/
@menelic menelic changed the title Implement Massively Multilingual Speech - Meta's Open Source moldel with less than half of Whispers error rate Implement Massively Multilingual Speech - Meta's Open Source model with less than half of Whispers error rate May 23, 2023
@hayabhay hayabhay added the enhancement New feature or request label Jul 5, 2023
@hayabhay hayabhay self-assigned this Jul 5, 2023
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees

@hayabhay hayabhay

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@menelic @hayabhay