VI
VibeVoice-ASR-BitNet
microsoft
ID: vibevoice-asr-bitnet
open weights·Active·audio speech·Updated Jul 24, 2026
VibeVoice-ASR-BitNet is a 323M-parameter automatic speech recognition model developed by microsoft. Built on the VibeVoiceForASRTraining architecture using ggml. Supports en, zh, fr, it, ko, pt, vi language(s). Released on 2026-07-24 with 115 likes and 3,864 downloads on Hugging Face.
VibeVoice-ASR-BitNet
Model Overview
VibeVoice-ASR-BitNet is a 323M-parameter automatic speech recognition model developed by microsoft. Built on the VibeVoiceForASRTraining architecture. Supports en, zh, fr, it, ko, pt, vi. Released on 2026-07-24.
📊 Quick Specs
Specification Table
| Specification | Value |
|---|---|
| Parameters | 323M |
| Architecture | VibeVoiceForASRTraining |
| Task | automatic speech recognition |
| Modality | audio, text |
| License | MIT |
| Framework | ggml |
| MoE | No |
| Languages | en, zh, fr, it, ko, pt, vi |
✨ Key Features
- 323M parameters
- Built on VibeVoiceForASRTraining architecture (ggml)
- Primary task: automatic speech recognition (audio, text modality)
- Language support: en, zh, fr, it, ko, pt, vi
- Open-weights under MIT license — self-hostable and fine-tunable
📈 Community Adoption
- 115 likes on Hugging Face
- 3,864 downloads on Hugging Face
🔗 Resources
- Hugging Face Hub: VibeVoice-ASR-BitNet on Hugging Face
- Paper: arXiv
📜 License & Access
MIT — Open-weights model available for download, fine-tuning, and self-hosted deployment.
