Cohere Transcribe Arabic 07 2026 MLX Mixed 2bit3bit4bit
A dynamically quantized MLX build of CohereLabs/cohere-transcribe-arabic-07-2026 (bilingual Arabic + English, dialects, code-switching). To our knowledge the first sub-1GB quantized release of this model.
Model source
- Kind
- Text model
- File size
- 803 MB
- Base model
- CohereLabs/cohere-transcribe-arabic-07-2026
- Version
- vmodel
- Updated
- Oct 26, 2026
- Downloads
- 32
- Source
- Hugging Face
Source description
Cohere Transcribe Arabic 07-2026 — MLX Mixed 2-bit/3-bit/4-bit
A dynamically quantized MLX build of CohereLabs/cohere-transcribe-arabic-07-2026 (bilingual Arabic + English, dialects, code-switching). To our knowledge the first sub-1GB quantized release of this model.
Bit-widths are assigned per module from two independent quantization-
sensitivity scans (one on this model, one on its English base model). The
published allocation keeps the safer, higher bit-width for each module. Most
of the encoder runs at 2-bit; the empirically fragile groups (decoder, last
encoder blocks) stay at 3/4-bit. The rule map ships in this repo as
quant_bitmap.json.
Key Metrics
| Metric | Value |
|---|---|
| Size | 806 MB (vs 4.13 GB FP16 — 5.1x smaller) |
| Effective bits/param | 3.456 |
| WER FLEURS ar_eg (full 428) | 5.09% (FP16: 4.74%) |
| WER LibriSpeech clean/other (full) | 1.14% / 2.55% (composite 1.84%) |
| RTFx (M4 Air, MLX) | ~19x on Arabic — 2x the FP16 speed (9.8x) |
Arabic WER is scored with standard Arabic normalization (diacritics stripped, hamza-alif/ya/ta-marbuta folded); compare deltas, not absolute numbers across papers.
Quantization layout
| Component | Quantization |
|---|---|
| Encoder (most groups) | 2-bit affine, group size 64 |
| Encoder blocks 36–47 (attn/ffn/pointwise, per bitmap) | 3–4-bit |
| Decoder + head | 4-bit |
| Norms / embeddings / mel frontend | FP16 |
1x1 Conv1d layers are converted to Linear equivalents to enable quantization.
Architecture
- Base model: Cohere Transcribe Arabic 07-2026 (~2B params, bilingual ar+en)
- Encoder: FastConformer (48 layers, d=1280)
- Decoder: Transformer (8 layers, d=1024)
- Tokenizer: SentencePiece (16,384 tokens)
Usage
Requires mlx-audio installed from git main:
pip install "mlx-audio[stt] @ git+https://github.com/Blaizzy/mlx-audio.git"
# apply the loader patch shipped in this repo (fixes two upstream
# quantized-reload bugs; see mlx_audio_cohere_quant_patch.py)
from mlx_audio_cohere_quant_patch import apply_patch
apply_patch()
from mlx_audio.stt import load
model = load("MarkChen1214/cohere-transcribe-arabic-07-2026-MLX-Mixed-2bit3bit4bit")
# Arabic (incl. dialects and ar-en code-switching)
result = model.generate(audio="audio.wav", language="ar", punctuation=True)
print(result.text)
# English works too
result = model.generate(audio="audio_en.wav", language="en", punctuation=True)
Eval Results (full datasets, seed=42)
| Dataset | Samples | WER | RTFx |
|---|---|---|---|
| FLEURS ar_eg test | 428 | 5.09% | 19.0x |
| LibriSpeech test-clean | 2,620 | 1.14% | 17.9x |
| LibriSpeech test-other | 2,939 | 2.55% | 18.9x |
English scored with the HF Open ASR Leaderboard methodology (Whisper EnglishTextNormalizer + jiwer).
License
MIT — use it however you like, attribution appreciated.
The base model (CohereLabs/cohere-transcribe-arabic-07-2026) is Apache 2.0; its notices apply to the underlying weights.
Sources
1 source
Sources
1 sourceVerified Oct 26
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
3 excerpts
Source excerpts
3 excerpts--- license: mit base_model: CohereLabs/cohere-transcribe-arabic-07-2026 tags: - automatic-speech-recognition - mlx - speech-recognition - transcription - audio - apple - macos - on-device - quantized - mixed-precision - dynamic-quantization - arabic - arabic-asr - arabic-dialect - code-switching - 2bit - 3bit - 4bit language: - ar - en pipeline_tag: automatic-speech-recognition library_name: mlx --- # Cohere Transcribe Arabic 07-2026 — MLX Mixed 2-bit/3-bit/4-bit A **dynamically quantized** MLX build of [CohereLabs/cohere-transcribe-arabic-07-2026](https://huggingface.co/CohereLabs/cohere-transcribe-arabic-07-2026) (bilingual Arabic + English, dialects, code-switching). To our knowledge the first sub-1GB quantized release of this model. Bit-widths are assigned per module from **two independent quantization- sensitivity scans** (one on this model, one on its English base model). The published allocation keeps the safer, higher bit-width for each module. Most of the encoder runs at **2-bit**; the empirically fragile groups (decoder, last encoder blocks) stay at 3/4-bit. The rule map ships in this repo as [`quant_bitmap.json`](./quant_bitmap.json). ## Key Metrics | Metric | Value | |--------|-------| | **Size** | 806 MB (vs 4.13 GB FP16 — 5.1x smaller) | | **Effective bits/param** | 3.456 | | **WER FLEURS ar_eg (full 428)** | 5.09% (FP16: 4.74%) | | **WER LibriSpeech clean/other (full)** | 1.14% / 2.55% (composite 1.84%) | | **RTFx (M4 Air, MLX)** | ~19x on Arabic — **2x the FP16 speed** (9.8x) | Arabic WER is scored with standard Arabic normalization (diacritics stripped, hamza-alif/ya/ta-marbuta folded); compare deltas, not absolute numbers across papers. ## Quantization layout | Component | Quantization | |-----------|-------------| | Encoder (most groups) | 2-bit affine, group size 64 | | Encoder blocks 36–47 (attn/ffn/pointwise, per bitmap) | 3–4-bit | | Decoder + head | 4-bit | | Norms / embeddings / mel frontend | FP16 | 1x1 Conv1d layers are converted to Linear equivalents to enable quantization. ## Architecture - **Base model**: Cohere Transcribe Arabic 07-2026 (~2B params, bilingual ar+en) - **Encoder**: FastConformer (48 layers, d=1280) - **Decoder**: Transformer (8 layers, d=1024) - **Tokenizer**: SentencePiece (16,384 tokens) ## Usage Requires [mlx-audio](https://github.com/Blaizzy/mlx-audio) installed from git...
Source context: 32 downloads · 1 likes · Pipeline automatic-speech-recognition · Library mlx · Repo MarkChen1214/cohere-transcribe-arabic-07-2026-MLX-Mixed-2bit3bit4bit
Source context: 265 downloads · 1 likes · Pipeline automatic-speech-recognition · Library mlx · Repo MarkChen1214/cohere-transcribe-arabic-07-2026-MLX-Mixed-2bit3bit4bit
