Speech Recognition Models
Collection
2 items • Updated
This repository contains a fully fine-tuned version of the Qwen3-ASR model.
Using 1000 samples from CommonVoice 17 as the evaluation dataset, the following metrics demonstrate a significant improvement over the base model:
| Metric | Base Model (Original) | Fine-tuned Model |
|---|---|---|
| Raw WER | 29.20% | 16.83% |
| Normalized WER | 26.24% | 13.68% |
Due to the specific licensing and characteristics of the dataset used during the fine-tuning process, this model is strictly prohibited for commercial use. It is intended for research, evaluation.