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

update README

Browse Source 
Added a section on LoRA fine-tuning to the ASR documentation.
This commit is contained in:
YaoyaoChang
2026-01-27 21:01:40 +08:00
committed by GitHub
parent 0e1a0d39fd
commit c435ae05d5
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/vibevoice-asr.md
+6 -4
View File
@@ -86,6 +86,12 @@ python demo/vibevoice_asr_gradio_demo.py --model_path microsoft/VibeVoice-ASR --
python demo/vibevoice_asr_inference_from_file.py --model_path microsoft/VibeVoice-ASR --audio_files [add a audio path here] python demo/vibevoice_asr_inference_from_file.py --model_path microsoft/VibeVoice-ASR --audio_files [add a audio path here]
``` ```
## Finetuning
LoRA (Low-Rank Adaptation) fine-tuning is supported. See [Finetuning](../finetuning-asr/README.md) for detailed guide.
## Results ## Results
### Multilingual ### Multilingual
@@ -114,10 +120,6 @@ python demo/vibevoice_asr_inference_from_file.py --model_path microsoft/VibeVoic
| MLC-Challenge | Average | 3.42 | 14.81 | 15.66 | 12.07| | MLC-Challenge | Average | 3.42 | 14.81 | 15.66 | 12.07|
## Finetuning
LoRA (Low-Rank Adaptation) fine-tuning is supported. See [Finetuning](../finetuning-asr/README.md) for detailed guide.
## 📄 License ## 📄 License
This project is licensed under the [MIT License](../LICENSE). This project is licensed under the [MIT License](../LICENSE).