---
title: Phonon-2
canonical_url: "https://www.modelscope.cn/models/mlx-community/Phonon-2"
md_url: "https://www.modelscope.cn/models/mlx-community/Phonon-2.md"
repository: mlx-community/Phonon-2
last_updated: 2026-10-17
license: cc-by-4.0
model_type:
  - phonon2
base_model:
  - FermionResearch/Phonon-2
base_model_relation: finetune
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 13
stars: 0
tags:
  - mlx
  - mlx-audio
  - phonon2
  - parakeet
  - five-value
  - apple-silicon
---

# Phonon-2

> Phonon-2 - mlx-community 在 ModelScope 开源的模型。English speech recognition with Fermion Research's Phonon-2, derived from NVIDIA Parakeet TDT 0.6B v3. Preconverted five-value weights; approximately 350 MB. No converter or Fermion runtime needed. Requires…

mlx-community/Phonon-2 是 ModelScope 魔搭社区上的机器学习模型，采用 cc-by-4.0 许可，基于 FermionResearch/Phonon-2 构建。

- **Repository**: mlx-community/Phonon-2
- **License**: cc-by-4.0
- **Base model**: FermionResearch/Phonon-2
- **Tags**: mlx, mlx-audio, phonon2, parakeet, five-value, apple-silicon
- **Downloads**: 13
- **Stars**: 0
- **Last updated**: 2026-10-17

Source: https://www.modelscope.cn/models/mlx-community/Phonon-2

---

# Phonon-2 for MLX

English speech recognition with [Fermion Research's Phonon-2](https://huggingface.co/FermionResearch/Phonon-2),
derived from [NVIDIA Parakeet TDT 0.6B v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3).
Preconverted five-value weights; approximately 350 MB. No converter or Fermion runtime needed.
Requires mlx-audio with Phonon-2 support.

```python
from mlx_audio.stt import load

model = load("mlx-community/Phonon-2")
result = model.generate("audio.wav", chunk_duration=30, overlap_duration=2)
print(result.text)
```

Supports token timestamps and overlapping chunk output, not live-input streaming.
Validated against the official packed runtime on six clips using MLX 0.32.4.

Weights: [CC-BY-4.0](LICENSE-WEIGHTS-CC-BY-4.0.txt). Copyright Fermion Research and NVIDIA.
Encoder codes are repacked into two MLX 2-bit planes; row palettes remain fp16 and dense tables use bf16.
See [NOTICE](NOTICE) for attribution.