---
title: Fun-ASR-MLT-Nano-2512-fp16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Fun-ASR-MLT-Nano-2512-fp16"
md_url: "https://www.modelscope.cn/models/mlx-community/Fun-ASR-MLT-Nano-2512-fp16.md"
repository: mlx-community/Fun-ASR-MLT-Nano-2512-fp16
last_updated: 2025-12-16
model_type:
  - funasr
base_model:
  - FunAudioLLM/Fun-ASR-MLT-Nano-2512
base_model_relation: finetune
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
downloads: 127
stars: 0
tags:
  - mlx
  - funasr
  - speech-recognition
  - speech-to-text
  - stt
---

# Fun-ASR-MLT-Nano-2512-fp16

> Fun-ASR-MLT-Nano-2512-fp16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Fun-ASR-MLT-Nano-2512-fp16

mlx-community/Fun-ASR-MLT-Nano-2512-fp16 是 ModelScope 魔搭社区上的机器学习模型，基于 FunAudioLLM/Fun-ASR-MLT-Nano-2512 构建。

- **Repository**: mlx-community/Fun-ASR-MLT-Nano-2512-fp16
- **Base model**: FunAudioLLM/Fun-ASR-MLT-Nano-2512
- **Tags**: mlx, funasr, speech-recognition, speech-to-text, stt
- **Downloads**: 127
- **Stars**: 0
- **Last updated**: 2025-12-16

Source: https://www.modelscope.cn/models/mlx-community/Fun-ASR-MLT-Nano-2512-fp16

---

# mlx-community/Fun-ASR-MLT-Nano-2512-fp16

This model was converted to MLX format from [FunAudioLLM/Fun-ASR-MLT-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512) using [mlx-audio-plus](https://github.com/DePasqualeOrg/mlx-audio-plus) version **0.1.4**.

## Features

| Feature | Description |
|---------|-------------|
| **Multilingual** | Supports 31 languages with focus on East and Southeast Asian languages |
| **Chinese dialects** | Supports 7 major Chinese dialects |
| **Code-switching** | Handles mixed-language speech within sentences |
| **Translation** | Translate speech directly to English text |
| **Custom prompting** | Guide recognition with domain-specific context |
| **Streaming** | Real-time token-by-token output |

## Installation

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

## Usage

### Basic Transcription

```python
from mlx_audio.stt.models.funasr import Model

# Load the model
model = Model.from_pretrained("mlx-community/Fun-ASR-MLT-Nano-2512-fp16")

# Transcribe audio
result = model.generate("audio.wav")
print(result.text)
# Output: "The quick brown fox jumps over the lazy dog."

print(f"Duration: {result.duration:.2f}s")
print(f"Language: {result.language}")
```

### Translation (Speech to English Text)

```python
# Translate Chinese/Japanese/etc. audio to English
result = model.generate(
    "chinese_speech.wav",
    task="translate",
    target_language="en"
)
print(result.text)  # English translation
```

### Custom Prompting

Provide context to improve recognition accuracy for specialized domains:

```python
# Medical transcription
result = model.generate(
    "doctor_notes.wav",
    initial_prompt="Medical consultation discussing cardiac symptoms and treatment options."
)

# Technical content
result = model.generate(
    "tech_podcast.wav",
    initial_prompt="Discussion about machine learning, APIs, and software development."
)
```

### Streaming Output

Get real-time output as the model generates:

```python
# Print tokens as they're generated
result = model.generate("audio.wav", verbose=True)
# Tokens stream to stdout in real-time

# Or use the streaming generator
for chunk in model.generate("audio.wav", stream=True):
    print(chunk, end="", flush=True)
```

## Supported Languages

See [original model](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512) for the full list of supported languages.