Microsoft releases VibeVoice-ASR-BitNet as a multilingual speech-recognition model
microsoft · hf · 2026-07-24
Microsoft releases VibeVoice-ASR-BitNet, a new multilingual speech-recognition model
Microsoft has published VibeVoice-ASR-BitNet, an automatic-speech-recognition model release with multilingual support and multiple deployment-oriented formats, including GGUF, ggml, and safetensors.
The release is positioned around efficient inference, with tags highlighting BitNet, quantization, and CPU inference, suggesting a focus on lightweight speech recognition deployment rather than a research paper.
More from Models
- Kimi K3 is "open source until you get successful": $20M revenue triggers extra license terms — alex_verem · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27