---
license: apache-2.0
language:
- multilingual
tags:
- automatic-speech-recognition
- mlx
- apple-silicon
- wav2vec2
- ctc
- multilingual
- low-resource
base_model: facebook/omniASR-CTC-3B
library_name: mlx
pipeline_tag: automatic-speech-recognition
---

# Omnilingual ASR — CTC 3B (MLX 4-bit)

MLX-compatible 4-bit quantization of Meta's Omnilingual ASR CTC-3B model for
on-device inference on Apple Silicon (M2 Pro / M3 / M4 recommended). Trades
~1 GB of extra disk versus [CTC-1B 4-bit](https://huggingface.co/aufklarer/Omnilingual-ASR-CTC-1B-MLX-4bit)
for measurably better accuracy on low-resource languages per Meta's published
FLEURS results.

Omnilingual ASR is a wav2vec 2.0-style encoder-only model with a linear CTC
head, trained by Meta for speech recognition across **1,600+ languages**. The
CTC variant is language-agnostic at inference time.

## Model

| | |
|---|---|
| Parameters | ~3 B |
| Format | MLX safetensors (quantized linear layers + fp16 features) |
| Quantization | 4-bit per-group min-max, group size 64 |
| Sample rate | 16 kHz (raw waveform input) |
| Frame rate | 50 fps |
| Max duration | 40 s |
| Languages | 1,600+ |
| Vocabulary | 10,288 SentencePiece tokens |

Full architecture details (num_layers / model_dim / ffn_dim) are in
`config.json`.

## Files

| File | Description |
|---|---|
| `model.safetensors` | 4-bit quantized transformer weights + fp16 conv frontend |
| `tokenizer.model`   | SentencePiece tokenizer |
| `config.json`       | Architecture + quantization metadata |

## Usage

```python
import mlx.core as mx
from safetensors import safe_open

weights = {}
with safe_open("model.safetensors", framework="mlx") as f:
    for k in f.keys():
        weights[k] = f.get_tensor(k)
```

Swift inference is provided by [speech-swift](https://github.com/soniqo/speech-swift).

## Source

- Upstream model: [facebook/omniASR-CTC-3B](https://huggingface.co/facebook/omniASR-CTC-3B)
- Paper: [*Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages*](https://arxiv.org/abs/2511.09690)
- Meta blog: [Omnilingual ASR announcement](https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/)

## Links

- [speech-swift](https://github.com/soniqo/speech-swift) — Apple SDK
- [soniqo.audio](https://soniqo.audio) — website
- [blog](https://soniqo.audio/blog)

## License

Apache 2.0 (inherited from upstream).

---

- **Guide**: [soniqo.audio/guides/omnilingual](https://soniqo.audio/guides/omnilingual)
- **Docs**: [soniqo.audio](https://soniqo.audio)
- **GitHub**: [soniqo/speech-swift](https://github.com/soniqo/speech-swift)