update readme
Browse files- .gitattributes +1 -0
- README.md +5 -0
- figures/MOS-preference.png +0 -0
- figures/VibeVoice.jpg +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.jpg filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -16,6 +16,11 @@ The model can synthesize speech up to **90 minutes** long with up to **4 distinc
|
|
| 16 |
|
| 17 |
➡️ **Code:** [microsoft/VibeVoice-Code](https://github.com/microsoft/VibeVoice)
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## Training details
|
| 20 |
Transformer-based Large Language Model (LLM) integrated with specialized acoustic and semantic tokenizers and a diffusion-based decoding head.
|
| 21 |
- LLM: [Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) for this release.
|
|
|
|
| 16 |
|
| 17 |
➡️ **Code:** [microsoft/VibeVoice-Code](https://github.com/microsoft/VibeVoice)
|
| 18 |
|
| 19 |
+
<p align="left">
|
| 20 |
+
<img src="figures/VibeVoice.jpg" alt="VibeVoice Overview" height="250px" style="margin-right: 10px;">
|
| 21 |
+
<img src="figures/MOS-preference.png" alt="MOS Preference Results" height="260px">
|
| 22 |
+
</p>
|
| 23 |
+
|
| 24 |
## Training details
|
| 25 |
Transformer-based Large Language Model (LLM) integrated with specialized acoustic and semantic tokenizers and a diffusion-based decoding head.
|
| 26 |
- LLM: [Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) for this release.
|
figures/MOS-preference.png
ADDED
|
figures/VibeVoice.jpg
ADDED
|
Git LFS Details
|