🤗 we just opensourced our tiny beast on @huggingface >0.9B ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min au…

🤗 we just opensourced our tiny beast on @huggingface >0.9B ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one generation >Multi-speaker diarization for meetings, interruptions, and overlapping voices >Hotword customization for names, terms, and domain-specific vocabulary >~100 token/s on NVIDIA RTX 4090, RTF ~0.017 thank you @sgl_project @vllm_project @Prince_Canuma @lllucas for day-0 support 💖 try it live👇 https://x.com/MosiAI_Official/status/2075059157443756245/video/1 Media 🤗 MOSS-Transcribe-Diarize-0.9B is now open source on @huggingface. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one ge…

Source: Clem Delangue (X) | 2026-07-09