AK#33
MOSS-Audio just hit #1 on @huggingface Trending.
Speech. Sound. Music.
One open audio-language model.
Try it: Hugging Face: https://huggingface.co/collections/OpenMOSS-Team/moss-audio GitHub: https://github.com/OpenMOSS/MOSS-Audio
Users expressed frustration with MOSS-Audio's unclear language support details on Hugging Face, as they often must dig through papers and benchmarks instead of finding the information readily available.
No Digg Deeper questions have been answered for this story yet.
@MosiAI_Official @_akhaliq @huggingface I wish audio model made language support much clearer. Too often you have to dig through papers, benchmarks, examples, and scattered notes just to understand whether a model actually supports a language or merely might work with it. A simple table would save everyone time.