Streaming audio S2TT Example/Guidance

facebookresearch / seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

Other

10.94k stars 1.06k forks source link

Streaming audio S2TT Example/Guidance #59

Open SeeRich opened 1 year ago

SeeRich commented 1 year ago

I am interested in streaming audio chunks and performing continuous S2TT. Is this possible with the current code? If so, any guidance would be much appreciated!

jmp84 commented 1 year ago

@SeeRich it's not possible with the current code AFAIK.

kauterry commented 1 year ago

We don't have support for streaming translation yet.

fishfree commented 1 year ago

Why close this issue. It's an important feature request. :-)

annasun28 commented 10 months ago

This is supported with SeamlessStreaming models, see https://github.com/facebookresearch/seamless_communication/?tab=readme-ov-file#seamlessstreaming, see also the colab at https://fb.me/mt-neurips for an example of standalone inference or the demo code at https://huggingface.co/spaces/facebook/seamless-streaming/blob/main/README.md