Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
1–10 of 232 posts
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#2Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#3Wow, I didn't even know there was 7,000 documented languages in the world!
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#4> The MMS code and model weights are released under the CC-BY-NC 4.0 license.
Huge bummer. Prevents almost everyone from using this and recouping their costs.
I suppose motivated teams could reproduce the paper in a clean room, but that might also be subject to patents.
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#5Meta on a roll. any demo on how good the text to speech is ?
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#6Code: https://github.com/facebookresearch/fairseq/tree/main/exampl... Blog Post: https://ai.facebook.com/blog/multilingual-model-speech-recog... Paper: https://research.facebook.com/publications/scaling-speech-te... Languages coverage: https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mm...
Based on the availability of STT, TTS, and translation models available to download in that github repo, a real-life babelfish is 'only' some glue code away. Wild times we're living in.
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#7Wow, I didn't even know there was 7,000 documented languages in the world!
"According to the World Atlas of Languages' methodology, there are around 8324 languages, spoken or signed, documented by governments, public institutions and academic communities. Out of 8324, around 7000 languages are still in use."
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#8This looks huge. Anyone know how this compares with Whisper in terms of quality and speed?
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#9> The MMS code and model weights are released under the CC-BY-NC 4.0 license. Huge bummer. Prevents almost everyone from using this and recouping their costs. I suppose motivated teams could reproduce the paper in a clean room, but that might also be subject to patents.
Id imagine you could use inference from this as training for a commercial model, as that isn't currently protected under copyright.
Re: Meta AI announces Massive Multilingual Speech code, models for 1000+ languages
#10So many so-called overnight AI gurus hyping about their snake-oil product and screaming about 'Meta is dying' [0] and 'It is over for Meta' but little of them actually do research in AI and drive the field forward and this once again shows that Meta has always been a consistent contributor to AI research, especially in vision systems.
All we can just do is take, take, take the code. But this time, the code's license is CC-BY-NC 4.0. Which simply means:
Take it, but no grifting allowed.