---
title: SenseVoiceSmall
canonical_url: "https://www.modelscope.cn/models/mlx-community/SenseVoiceSmall"
md_url: "https://www.modelscope.cn/models/mlx-community/SenseVoiceSmall.md"
repository: mlx-community/SenseVoiceSmall
last_updated: 2026-03-12
license: other
model_type:
  - sensevoice
base_model:
  - FunAudioLLM/SenseVoiceSmall
base_model_relation: finetune
parameters: 234.0M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 176
stars: 1
tags:
  - mlx
  - speech-to-text
  - speech
  - sts
  - mlx-audio
---

# SenseVoiceSmall

> SenseVoiceSmall - mlx-community 在 ModelScope 开源的模型。This model was converted to MLX format from FunAudioLLM/SenseVoiceSmall using mlx-audio version 0.4.0.

mlx-community/SenseVoiceSmall 是 ModelScope 魔搭社区上的 234.0M 参数机器学习模型，采用 other 许可，基于 FunAudioLLM/SenseVoiceSmall 构建。

- **Repository**: mlx-community/SenseVoiceSmall
- **License**: other
- **Parameters**: 234.0M
- **Base model**: FunAudioLLM/SenseVoiceSmall
- **Tags**: mlx, speech-to-text, speech, sts, mlx-audio
- **Downloads**: 176
- **Stars**: 1
- **Last updated**: 2026-03-12

Source: https://www.modelscope.cn/models/mlx-community/SenseVoiceSmall

---

This model was converted to MLX format from [`FunAudioLLM/SenseVoiceSmall`](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) using mlx-audio version **0.4.0**.

Refer to the [original model card](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) for more details on the model.