Hacker News Reader

Yet again, Hindi (the major language in India) is not even in the samples. India is the largest user base of facebook (and probably 1/3rd of the engineers working there are Indians) but never will facebook put enough effort to contribute back. Only use the DAU from India in investor calls.

View on HN

By "samples" do you mean examples on the marketing/landing page? It sure looks like the model supports many major Indian languages like Telugu, Tamil & Kannada. https://huggingface.co/facebook/seamless-m4t-v2-large

Yeah, I kinda agree with the spirit of your comment; it sure would be nice to see a major Indian language like Telugu on their landing page for sure. But that's just my Indian-person bias speaking.

The lack of focus shows up in the results. The models never performs as good as french or spanish on Indian languages. This goes for Google, too.

slightly new to this area

is there an example notebook that shows how we can use this model with own sample audio and text? thanks!

I work on seamless and you can find sample code here: https://github.com/fairinternal/seamless_communication or in the HuggingFace space.

Reply on news.ycombinator.com