Microsoft Research has released VibeVoice-ASR-Streaming-7B, a unified streaming automatic speech recognition (ASR) model. This model offers continuous transcription of who said what, supports customized hotwords for domain-specific content, and includes multilingual capabilities for ten languages. It is available for use with libraries like Transformers and can be integrated into notebooks and local applications. AI
IMPACT Enables real-time, speaker-attributed transcription with customization for specific domains and multiple languages.
RANK_REASON Release of a specific model by a research division. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
- Google Colab
- Kaggle
- Microsoft Research
- microsoft/VibeVoice-ASR-Streaming-7B
- transformers
- VibeVoice
- VibeVoice-ASR-Streaming
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →