christian.schwarz/VibeVoice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update ASR README: multilingual

Browse Source
This commit is contained in:
YaoyaoChang
2026-01-27 20:58:10 +08:00
committed by GitHub
parent 4648c50ea0
commit 142a00112e
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/vibevoice-asr.md
+4 -1
View File
@@ -3,7 +3,7 @@
[![Hugging Face](https://img.shields.io/badge/HuggingFace-Collection-orange?logo=huggingface)](https://huggingface.co/microsoft/VibeVoice-ASR) [![Hugging Face](https://img.shields.io/badge/HuggingFace-Collection-orange?logo=huggingface)](https://huggingface.co/microsoft/VibeVoice-ASR)
[![Live Playground](https://img.shields.io/badge/Live-Playground-green?logo=gradio)](https://aka.ms/vibevoice-asr) [![Live Playground](https://img.shields.io/badge/Live-Playground-green?logo=gradio)](https://aka.ms/vibevoice-asr)
**VibeVoice-ASR** is a unified speech-to-text model designed to handle **60-minute long-form audio** in a single pass, generating structured transcriptions containing **Who (Speaker), When (Timestamps), and What (Content)**, with support for **Customized Hotwords**. **VibeVoice-ASR** is a unified speech-to-text model designed to handle **60-minute long-form audio** in a single pass, generating structured transcriptions containing **Who (Speaker), When (Timestamps), and What (Content)**, with support for **Customized Hotwords** and over **50 languages**.
**Model:** [VibeVoice-ASR-7B](https://huggingface.co/microsoft/VibeVoice-ASR)<br> **Model:** [VibeVoice-ASR-7B](https://huggingface.co/microsoft/VibeVoice-ASR)<br>
**Demo:** [VibeVoice-ASR-Demo](https://aka.ms/vibevoice-asr)<br> **Demo:** [VibeVoice-ASR-Demo](https://aka.ms/vibevoice-asr)<br>
@@ -22,6 +22,9 @@
- **📝 Rich Transcription (Who, When, What)**: - **📝 Rich Transcription (Who, When, What)**:
The model jointly performs ASR, diarization, and timestamping, producing a structured output that indicates *who* said *what* and *when*. The model jointly performs ASR, diarization, and timestamping, producing a structured output that indicates *who* said *what* and *when*.
- **🌍 Multilingual & Code-Switching Support**:
It supports over 50 languages, requires no explicit language setting, and natively handles code-switching within and across utterances. Language distribution can be found [here](#language-distribution)
## 🏗️ Model Architecture ## 🏗️ Model Architecture