Downloads · 30 days
0
kiiic/MNV-17-Qwen-fintune
MNV-17-Qwen-fintune is a machine learning model from kiiic. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository demonstrates the excellent performance of Qwen2.5-Omni and Qwen2-Audio models fine-tuned on the MNV-17 dataset for Nonverbal Vocalization (NV) ASR recognition tasks. It also provides inference scripts…
Downloads · 30 days
0
Access
Public
Updated Nov 10, 2025
Repo size
445 MB
Likes
4
Public
Click a slice to open those files.
.zip445 MB · 100%
From the Hugging Face model README
This repository demonstrates the excellent performance of Qwen2.5-Omni and Qwen2-Audio models fine-tuned on the MNV-17 dataset for Nonverbal Vocalization (NV) ASR recognition tasks. It also provides inference scripts for Qwen2.5-Omni and Qwen2-Audio.
Click here for interactive audio demo
Crucial Note: All demo samples are from speakers who were completely unseen during training.
This demonstrates that the model learned universal NV vocalization patterns rather than merely fitting specific speakers' habits, showcasing excellent cross-speaker generalization.
According to our paper experimental results:
| Model | Joint CER | NV Recognition Accuracy |
|---|---|---|
| Qwen2.5-Omni | 3.60% | 57.29% |
| Qwen2-Audio | 4.84% | 56.28% |
| SenseVoice | 8.71% | 57.29% |
| Paraformer | 5.70% | 28.64% |