---
title: CosyVoice2-0.5B-S3Tokenizer
canonical_url: "https://www.modelscope.cn/models/mlx-community/CosyVoice2-0.5B-S3Tokenizer"
md_url: "https://www.modelscope.cn/models/mlx-community/CosyVoice2-0.5B-S3Tokenizer.md"
repository: mlx-community/CosyVoice2-0.5B-S3Tokenizer
last_updated: 2025-07-07
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - FunAudioLLM/CosyVoice2-0.5B
base_model_relation: finetune
parameters: 123.7M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 452
stars: 1
---

# CosyVoice2-0.5B-S3Tokenizer

> CosyVoice2-0.5B-S3Tokenizer - mlx-community 在 ModelScope 开源的模型。mlx-community/CosyVoice2-0.5B-S3Tokenizer This model was converted to MLX format from FunAudioLLM/CosyVoice2-0.5B using mlx-audio. Refer to the original model card for more details on the model.

mlx-community/CosyVoice2-0.5B-S3Tokenizer 是 ModelScope 魔搭社区上的 123.7M 参数text-to-speech模型，采用 apache-2.0 许可，基于 FunAudioLLM/CosyVoice2-0.5B 构建。

- **Repository**: mlx-community/CosyVoice2-0.5B-S3Tokenizer
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 123.7M
- **Base model**: FunAudioLLM/CosyVoice2-0.5B
- **Downloads**: 452
- **Stars**: 1
- **Last updated**: 2025-07-07

Source: https://www.modelscope.cn/models/mlx-community/CosyVoice2-0.5B-S3Tokenizer

---

# mlx-community/CosyVoice2-0.5B-S3Tokenizer
This model was converted to MLX format from [`FunAudioLLM/CosyVoice2-0.5B`]() using mlx-audio.
Refer to the [original model card](https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B) for more details on the model.

## Use with mlx

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