Add technical report

#11
by bezzam HF Staff - opened
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -19,6 +19,7 @@ library_name: transformers
19
 
20
  **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**.
21
 
 
22
  ➡️ **Code:** [microsoft/VibeVoice](https://github.com/microsoft/VibeVoice)<br>
23
  ➡️ **Demo:** [VibeVoice-ASR-Demo](https://aka.ms/vibevoice-asr)
24
 
 
19
 
20
  **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**.
21
 
22
+ ➡️ **Technical Report:** [VibeVoice ASR Technical Report](https://huggingface.co/papers/2601.18184)<br>
23
  ➡️ **Code:** [microsoft/VibeVoice](https://github.com/microsoft/VibeVoice)<br>
24
  ➡️ **Demo:** [VibeVoice-ASR-Demo](https://aka.ms/vibevoice-asr)
25