---
title: distil-whisper-small-cantonese-onnx-alvanlii-20240404
canonical_url: "https://www.modelscope.cn/models/manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404"
md_url: "https://www.modelscope.cn/models/manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404.md"
repository: manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404
chinese_name: "distil-whisper-small-语音识别-粤语-onnx模型-20240404"
last_updated: 2024-08-14
license: "Apache License 2.0"
pipeline_tag: auto-speech-recognition
tasks:
  - auto-speech-recognition
library_name:
  - onnx
  - pytorch
frameworks:
  - Pytorch
downloads: 15
stars: 0
---

# distil-whisper-small-cantonese-onnx-alvanlii-20240404

> distil-whisper-small-cantonese-onnx-alvanlii-20240404 - manyeyes 在 ModelScope 开源的模型。distil-whisper-small-语音识别-粤语-onnx模型-20240404

manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404 是 ModelScope 魔搭社区上的auto-speech-recognition模型，采用 Apache License 2.0 许可。

- **Repository**: manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404
- **License**: Apache License 2.0
- **Tasks**: auto-speech-recognition
- **Downloads**: 15
- **Stars**: 0
- **Last updated**: 2024-08-14

Source: https://www.modelscope.cn/models/manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404

---

### 当前模型源自：https://huggingface.co/alvanlii/distil-whisper-small-cantonese/blob/main/model.safetensors。
# Distil-Whisper Small zh-HK - Alvin

- This model is a distilled version of [alvanlii/whisper-small-cantonese](https://huggingface.co/alvanlii/whisper-small-cantonese) on the Cantonese language. 
- Achieves a 9.7 CER (without punctuations), 11.59 CER (with punctuations) on Common Voice 16.0.
- Has 3 decoder layers instead of regular 12 of the Whisper small model.
- Uses ~2GB of GPU VRAM

## Training and evaluation data
For training,
- CantoMap: Winterstein, Grégoire, Tang, Carmen and Lai, Regine (2020) "CantoMap: a Hong Kong Cantonese MapTask Corpus", in Proceedings of The 12th Language Resources and Evaluation Conference, Marseille: European Language Resources Association, p. 2899-2906.
- Cantonse-ASR: Yu, Tiezheng, Frieske, Rita, Xu, Peng, Cahyawijaya, Samuel, Yiu, Cheuk Tung, Lovenia, Holy, Dai, Wenliang, Barezi, Elham, Chen, Qifeng, Ma, Xiaojuan, Shi, Bertram, Fung, Pascale (2022) "Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset", 2022. Link: https://arxiv.org/pdf/2201.02419.pdf
- Common Voice yue and zh-HK train sets

For evaluation, Common Voice 16.0 yue Test set is used.

## Comparisons to Whisper Small
||`alvanlii/distil-whisper-small-cantonese`|`alvanlii/whisper-small-cantonese`|
|--|--|--|
|CER (lower is better)|0.097|0.089|
|GPU Inference time (sdpa) [s/sample]|0.027|0.055|
|GPU Inference (regular) [s/sample]|0.027|0.308|
|CPU Inference [s/sample]|1.3|2.57|
|Params [M]|157|242|


SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/manyeyes/distil-whisper-small-cantonese-onnx-alvanlii-20240404.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>