---
title: whisper-small.en-asr-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/whisper-small.en-asr-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/whisper-small.en-asr-8bit.md"
repository: mlx-community/whisper-small.en-asr-8bit
last_updated: 2026-01-16
license: apache-2.0
model_type:
  - whisper
architectures:
  - WhisperForConditionalGeneration
parameters: 69.5M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "vllm 0.9.2"
downloads: 27
stars: 0
tags:
  - audio
  - automatic-speech-recognition
  - hf-asr-leaderboard
  - mlx
  - speech-to-text
  - speech-to-speech
  - speech
  - "speech generation"
  - stt
---

# whisper-small.en-asr-8bit

> whisper-small.en-asr-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/whisper-small.en-asr-8bit This model was converted to MLX format from openai/whisper-small.en using mlx-audio version 0.2.10. Refer to the original model card for more details on the…

mlx-community/whisper-small.en-asr-8bit 是 ModelScope 魔搭社区上的 69.5M 参数机器学习模型，采用 apache-2.0 许可，可用 deploy_task vlm/text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/whisper-small.en-asr-8bit
- **License**: apache-2.0
- **Parameters**: 69.5M
- **Inference backends**: deploy_task vlm/text/emb, vllm 0.9.2
- **Tags**: audio, automatic-speech-recognition, hf-asr-leaderboard, mlx, speech-to-text, speech-to-speech, speech, speech generation, stt
- **Downloads**: 27
- **Stars**: 0
- **Last updated**: 2026-01-16

Source: https://www.modelscope.cn/models/mlx-community/whisper-small.en-asr-8bit

---

# mlx-community/whisper-small.en-asr-8bit
This model was converted to MLX format from [`openai/whisper-small.en`](https://huggingface.co/openai/whisper-small.en) using mlx-audio version **0.2.10**.
Refer to the [original model card](https://huggingface.co/openai/whisper-small.en) for more details on the model.

## Use with mlx-audio

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

### CLI Example:
```bash
python -m mlx_audio.stt.generate --model mlx-community/whisper-small.en-asr-8bit --audio "audio.wav"
```
### Python Example:
```python
from mlx_audio.stt.utils import load_model
from mlx_audio.stt.generate import generate_transcription
model = load_model("mlx-community/whisper-small.en-asr-8bit")
transcription = generate_transcription(
    model=model,
    audio_path="path_to_audio.wav",
    output_path="path_to_output.txt",
    format="txt",
    verbose=True,
)
print(transcription.text)
```