---
title: belle-whisper-large-v2-zh-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/belle-whisper-large-v2-zh-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/belle-whisper-large-v2-zh-8bit.md"
repository: mlx-community/belle-whisper-large-v2-zh-8bit
last_updated: 2026-05-30
license: apache-2.0
model_type:
  - whisper
architectures:
  - WhisperForConditionalGeneration
parameters: 438.5M
tensor_type:
  - U32
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 19
stars: 0
tags:
  - mlx
  - mlx-audio
  - whisper
  - automatic-speech-recognition
  - audio
---

# belle-whisper-large-v2-zh-8bit

> belle-whisper-large-v2-zh-8bit - mlx-community 在 ModelScope 开源的模型。Belle-whisper-large-v2-zh 8bit

mlx-community/belle-whisper-large-v2-zh-8bit 是 ModelScope 魔搭社区上的 438.5M 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: mlx-community/belle-whisper-large-v2-zh-8bit
- **License**: apache-2.0
- **Parameters**: 438.5M
- **Tags**: mlx, mlx-audio, whisper, automatic-speech-recognition, audio
- **Downloads**: 19
- **Stars**: 0
- **Last updated**: 2026-05-30

Source: https://www.modelscope.cn/models/mlx-community/belle-whisper-large-v2-zh-8bit

---

# Belle-whisper-large-v2-zh 8bit

This model was converted to MLX format from [BELLE-2/Belle-whisper-large-v2-zh](https://huggingface.co/BELLE-2/Belle-whisper-large-v2-zh).

## Use with MLX Audio

```bash
pip install mlx-audio
```

```python
from mlx_audio.stt import load

model = load("mlx-community/Belle-whisper-large-v2-zh-8bit")
result = model.generate("audio.wav")
print(result.text)
```