Add technical report
#11
by bezzam HF Staff - opened
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 |
|