---
language:
- el
- en
license: cc-by-4.0
library_name: mlx-audio
base_model: KIEFERSA/Sophea-Canary-ASR
pipeline_tag: automatic-speech-recognition
tags:
- automatic-speech-recognition
- speech-translation
- speech
- audio
- mlx
- mlx-audio
- apple-silicon
- canary
- FastConformer
- NeMo
- greek
- english
- bilingual
- multitask
datasets:
- google/fleurs
metrics:
- wer
- cer
model-index:
- name: Sophea-Canary-ASR-mlx
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      type: google/fleurs
      name: FLEURS (Greek)
      config: el_gr
      split: test
    metrics:
    - type: wer
      value: 9.36
      name: WER
    - type: cer
      value: 3.95
      name: CER
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      type: google/fleurs
      name: FLEURS (English)
      config: en_us
      split: test
    metrics:
    - type: wer
      value: 7.33
      name: WER
    - type: cer
      value: 3.60
      name: CER
---

# Sophea-Canary-ASR — MLX (bf16)

**Greek 🇬🇷 / English 🇬🇧 speech recognition & translation on Apple Silicon.**

MLX conversion of [`KIEFERSA/Sophea-Canary-ASR`](https://huggingface.co/KIEFERSA/Sophea-Canary-ASR)
— a bilingual fine-tune of NVIDIA's [`canary-1b-v2`](https://huggingface.co/nvidia/canary-1b-v2)
(978M params: FastConformer encoder + Transformer attention decoder). This repo runs
natively on Apple Silicon via [`mlx-audio`](https://github.com/Blaizzy/mlx-audio), no
PyTorch or NeMo required.

## Capabilities

| Task | `source_lang` → `target_lang` |
|---|---|
| Greek ASR | `el` → `el` |
| English ASR | `en` → `en` |
| Greek → English translation | `el` → `en` |

- **Weights:** bfloat16, ~1.9 GB
- **Sample rate:** 16 kHz mono (auto-resampled from any input)
- **Speed:** faster than real-time on M-series (RTF ≈ 0.11, bf16)

## Quickstart

```bash
pip install mlx-audio soundfile
```

```python
import re
import mlx_audio.stt as stt

model = stt.load("KIEFERSA/Sophea-Canary-ASR-mlx")

# Greek orthography helper (see note below)
def denormalize_greek(text: str) -> str:
    return re.sub(r"σ\b", "ς", text)   # word-final σ -> ς

# Greek ASR
out = model.generate("audio.wav", source_lang="el", target_lang="el")
print(denormalize_greek(out.text))

# Greek → English translation
print(model.generate("audio.wav", source_lang="el", target_lang="en").text)

# English ASR
print(model.generate("audio.wav", source_lang="en", target_lang="en").text)
```

### Greek final sigma

Canary's tokenizer represents final sigma as the medial form **σ**, so Greek output
comes out as e.g. `εποχήσ`. Restore standard orthography with the one-line
`denormalize_greek` helper above — a deterministic, lossless rule, since in Greek σ
never appears word-finally: `εποχήσ` → `εποχής`. Apply it to Greek (`target_lang="el"`)
output only; English and translation output need nothing.

## Performance

Full FLEURS `test` set (Greek n=650, English n=647; greedy, bf16):

| Language | WER | CER |
|---|---:|---:|
| Greek (`el_gr`) | **9.4%** | 3.95% |
| English (`en_us`) | **7.3%** | 3.60% |

*Greek WER measured after the word-final σ→ς step above.*

### NeMo vs MLX

Full FLEURS `test` WER, NeMo (`.nemo`) checkpoint vs this MLX (bf16) build:

| FLEURS test | NeMo | MLX (bf16) |
|---|---:|---:|
| Greek (`el_gr`) | 12.69 | **9.4** |
| English (`en_us`) | 12.9 | **7.3** |

*MLX figures measured over the full FLEURS test split (lowercase, punctuation-stripped).*

## Model details

| | |
|---|---|
| Architecture | FastConformer encoder (32 layers) + Transformer AED decoder (8 layers) |
| Parameters | ~978M |
| Tokenizer | Unified SentencePiece, 16,384 tokens |
| Base model | [`nvidia/canary-1b-v2`](https://huggingface.co/nvidia/canary-1b-v2) |
| Fine-tune | [`KIEFERSA/Sophea-Canary-ASR`](https://huggingface.co/KIEFERSA/Sophea-Canary-ASR) |
| Runtime | [`mlx-audio`](https://github.com/Blaizzy/mlx-audio) (Apple MLX) |
| Precision | bfloat16 |

## Also available

An int8-quantized variant (~1.1 GB, smaller & faster with a small accuracy trade-off)
can be produced with `mlx-audio`'s quantization, or loaded the same way.

## License & credits

Released under **CC-BY-4.0**, inheriting the license of `nvidia/canary-1b-v2`.
Fine-tune by KIEFERSA; MLX packaging for Apple Silicon via `mlx-audio` (Blaizzy).
```
@model{sophea_canary_asr_mlx,
  title  = {Sophea-Canary-ASR — MLX},
  author = {KIEFERSA},
  note   = {MLX conversion of a Greek/English canary-1b-v2 fine-tune},
  year   = {2026}
}
```