---
title: sam-audio-small-fp16
canonical_url: "https://www.modelscope.cn/models/mlx-community/sam-audio-small-fp16"
md_url: "https://www.modelscope.cn/models/mlx-community/sam-audio-small-fp16.md"
repository: mlx-community/sam-audio-small-fp16
last_updated: 2025-12-24
license: other
base_model:
  - facebook/sam-audio-small
base_model_relation: finetune
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 41
stars: 0
tags:
  - audio-to-audio
  - speech
  - "speech generation"
  - "voice isolation"
  - mlx
---

# sam-audio-small-fp16

> sam-audio-small-fp16 - mlx-community 在 ModelScope 开源的模型。mlx-community/sam-audio-small-fp16 This model was converted to MLX format from facebook/sam-audio-small using mlx-audio version 0.2.10. Refer to the original model card for more details on the model.

mlx-community/sam-audio-small-fp16 是 ModelScope 魔搭社区上的机器学习模型，采用 other 许可，基于 facebook/sam-audio-small 构建。

- **Repository**: mlx-community/sam-audio-small-fp16
- **License**: other
- **Base model**: facebook/sam-audio-small
- **Tags**: audio-to-audio, speech, speech generation, voice isolation, mlx
- **Downloads**: 41
- **Stars**: 0
- **Last updated**: 2025-12-24

Source: https://www.modelscope.cn/models/mlx-community/sam-audio-small-fp16

---

# mlx-community/sam-audio-small-fp16
This model was converted to MLX format from [`facebook/sam-audio-small`](https://huggingface.co/facebook/sam-audio-small) using mlx-audio version **0.2.10**.
Refer to the [original model card](https://huggingface.co/facebook/sam-audio-small) for more details on the model.

## Use with mlx
```bash
pip install -U mlx-audio
```

## Voice Isolation:
```python
from mlx_audio.sts import SAMAudio, SAMAudioProcessor, save_audio
import mlx.core as mx

# Load model and processor
processor = SAMAudioProcessor.from_pretrained("facebook/sam-audio-small-fp16")
model = SAMAudio.from_pretrained("facebook/sam-audio-small-fp16")

# Process inputs
batch = processor(
    descriptions=["speech"],
    audios=["path/to/audio.mp3"],
    # anchors=[[("+", 0.2, 0.5)]],  # Optional: temporal
)

# Separate audio
result = model.separate(
    audios=batch.audios,
    descriptions=batch.descriptions,
    sizes=batch.sizes,
    anchor_ids=batch.anchor_ids,
    anchor_alignment=batch.anchor_alignment,
    ode_decode_chunk_size=50,  # Chunked decoding for memory efficiency
)

# For long audio files, use separate_long().
# Note: This is slower than separate() but it is more memory efficient.
# result = model.separate_long(
#     audios=batch.audios,
#     descriptions=batch.descriptions,
#     chunk_seconds=10.0,
#     overlap_seconds=3.0,
#     anchor_ids=batch.anchor_ids,
#     anchor_alignment=batch.anchor_alignment,
#     ode_decode_chunk_size=50,  # Chunked decoding for memory efficiency
# )

# Save output
## Isolated speech
save_audio(result.target[0], "separated.wav", sample_rate=model.sample_rate)

## Residual audio (background music/noise/other sounds)
save_audio(result.residual[0], "residual.wav", sample_rate=model.sample_rate)

# Check memory usage
print(f"Peak memory: {result.peak_memory:.2f} GB")
```