---
license: apache-2.0
language:
- ar
- en
pipeline_tag: automatic-speech-recognition
tags:
- audio
- speech-recognition
- transcription
- arabic
- asr
- arabic-asr
- arabic-dialect
- arabic-speech-recognition
library_name: transformers
base_model:
- CohereLabs/cohere-transcribe-03-2026
---
# Cohere Transcribe Arabic
**Cohere Transcribe Arabic is an open source 2B-parameter Arabic automatic speech recognition model for speech-to-text transcription.** It is optimized for Arabic, Arabic Dialects, English, and Arabic-English code-switched speech.
Use it for Arabic ASR, Arabic audio transcription, dialectal Arabic speech recognition, and English speech-to-text. The model uses a Conformer encoder-decoder architecture and is supported natively in Transformers.
Based on the [Cohere Transcribe](https://huggingface.co/CohereLabs/cohere-transcribe-03-2026) architecture.
Developed by: [Cohere](https://cohere.com) and [Cohere Labs](https://cohere.com/research). Point of Contact: [Cohere Labs](https://cohere.com/research).
| Name |
cohere-transcribe-arabic-07-2026 |
| Architecture |
conformer-based encoder-decoder |
| Input |
audio waveform → log-Mel spectrogram. Audio is automatically resampled to 16kHz if necessary during preprocessing. Similarly, multi-channel (stereo) inputs are averaged to produce a single channel signal. |
| Output |
transcribed text |
| Model |
a large Conformer encoder extracts acoustic representations, followed by a lightweight Transformer decoder for token generation |
| Training objective |
supervised cross-entropy on output tokens |
| Languages |
|
| License |
Apache 2.0 |
✨Try the Cohere Transcribe Arabic [demo](https://huggingface.co/spaces/CohereLabs/cohere-transcribe-arabic-07-2026)✨
## Usage
Cohere Transcribe Arabic is supported natively in `transformers`. This is the recommended way to use the model for
offline inference. For online inference, see the vLLM integration example below.
```bash
pip install transformers>=5.4.0 torch huggingface_hub soundfile librosa sentencepiece protobuf accelerate
```
### Quick Start 🤗
Transcribe any audio file in a few lines:
```python
from transformers import AutoProcessor, CohereAsrForConditionalGeneration
from transformers.audio_utils import load_audio
from huggingface_hub import hf_hub_download
processor = AutoProcessor.from_pretrained("CohereLabs/cohere-transcribe-arabic-07-2026")
model = CohereAsrForConditionalGeneration.from_pretrained("CohereLabs/cohere-transcribe-arabic-07-2026", device_map="auto")
# Example: transcribe Arabic audio
audio_file = "your_audio.wav"
audio = load_audio(audio_file, sampling_rate=16000)
inputs = processor(audio, sampling_rate=16000, return_tensors="pt", language="ar")
inputs.to(model.device, dtype=model.dtype)
outputs = model.generate(**inputs, max_new_tokens=256)
text = processor.decode(outputs, skip_special_tokens=True)
print(text)
```
Long-form transcription
For audio longer than the feature extractor's `max_audio_clip_s`, the feature extractor automatically splits the waveform into chunks.
The processor reassembles the per-chunk transcriptions using the returned `audio_chunk_index`.
```python
from transformers import AutoProcessor, CohereAsrForConditionalGeneration
import time
processor = AutoProcessor.from_pretrained("CohereLabs/cohere-transcribe-arabic-07-2026")
model = CohereAsrForConditionalGeneration.from_pretrained("CohereLabs/cohere-transcribe-arabic-07-2026", device_map="auto")
audio = load_audio("your_long_audio.wav", sampling_rate=16000)
sr = 16000
duration_s = len(audio) / sr
print(f"Audio duration: {duration_s / 60:.1f} minutes")
inputs = processor(audio=audio, sampling_rate=sr, return_tensors="pt", language="ar")
audio_chunk_index = inputs.get("audio_chunk_index")
inputs.to(model.device, dtype=model.dtype)
start = time.time()
outputs = model.generate(**inputs, max_new_tokens=256)
text = processor.decode(outputs, skip_special_tokens=True, audio_chunk_index=audio_chunk_index, language="ar")[0]
elapsed = time.time() - start
rtfx = duration_s / elapsed
print(f"Transcribed in {elapsed:.1f}s — RTFx: {rtfx:.1f}")
print(text)
```
English transcription
The model also supports English. Specify `language="en"`:
```python
inputs = processor(audio, sampling_rate=16000, return_tensors="pt", language="en")
inputs.to(model.device, dtype=model.dtype)
outputs = model.generate(**inputs, max_new_tokens=256)
text = processor.decode(outputs, skip_special_tokens=True)
print(text)
```
### vLLM Integration
For production serving we recommend running via vLLM following the instructions below.
Run cohere-transcribe-arabic-07-2026 via vLLM
First install vLLM (refer to [vLLM installation instructions](https://docs.vllm.ai/en/latest/getting_started/installation/)):
```bash
uv venv --python 3.12 --seed
source .venv/bin/activate
uv pip install -U vllm==0.19.0 --torch-backend=auto
uv pip install vllm[audio]
uv pip install librosa
```
Start vLLM server
```bash
vllm serve CohereLabs/cohere-transcribe-arabic-07-2026 --trust-remote-code
```
Send request
```bash
curl -v -X POST http://localhost:8000/v1/audio/transcriptions \
-H "Authorization: Bearer $VLLM_API_KEY" \
-F "file=@$(realpath ${AUDIO_PATH})" \
-F "model=CohereLabs/cohere-transcribe-arabic-07-2026"
```
## Results
Open Universal Arabic ASR Leaderboard (as of 07.07.2026)
| Model |
AverageWER · CER |
SADAWER · CER |
Common VoiceWER · CER |
MASC cleanWER · CER |
MASC noisyWER · CER |
MGB-2WER · CER |
CasablancaWER · CER |
| Cohere Transcribe Arabic 07-2026 |
25.8711.80 |
37.4723.53 |
5.821.62 |
19.606.45 |
27.0710.13 |
15.548.40 |
49.7120.66 |
| OmniASR LLM 7B |
28.3212.52 |
41.6124.95 |
8.752.71 |
19.695.76 |
29.2910.66 |
14.137.10 |
56.4623.96 |
| OmniASR LLM 3B |
29.9613.77 |
46.1827.27 |
9.152.80 |
19.906.13 |
30.0311.27 |
14.227.06 |
60.2728.06 |
| OmniASR LLM 1B |
29.9613.40 |
43.8424.54 |
9.552.97 |
20.036.14 |
30.2611.18 |
15.347.56 |
60.6828.02 |
| Cohere Transcribe 03-2026 |
30.6716.37 |
60.1145.44 |
8.172.49 |
8.662.97 |
19.017.71 |
25.339.28 |
62.7130.31 |
| Qwen3-Omni 30B |
30.7113.67 |
44.8226.11 |
11.464.28 |
21.475.59 |
30.8511.28 |
13.096.20 |
62.5528.53 |
| NVIDIA Conformer-CTC (LM) |
32.9113.84 |
44.5223.76 |
8.802.77 |
23.745.63 |
34.2911.07 |
17.206.87 |
68.9032.97 |
| OmniASR LLM 300M |
32.9614.84 |
51.3829.10 |
12.034.04 |
20.666.22 |
32.4512.23 |
16.587.86 |
64.6429.61 |
| Gemma 4 E4B |
32.9813.71 |
43.4020.96 |
19.657.48 |
24.867.76 |
33.5912.25 |
17.728.67 |
58.6325.11 |
| Qwen3-ASR 1.7B |
33.3612.33 |
45.5319.90 |
16.905.06 |
24.375.72 |
34.2910.84 |
16.576.25 |
64.4726.23 |
| Voxtral-Small 24B |
34.4715.29 |
50.8228.85 |
15.255.54 |
23.967.06 |
34.4312.22 |
16.037.41 |
66.3030.64 |
| NVIDIA Conformer-CTC (greedy) |
34.7413.37 |
47.2622.54 |
10.603.05 |
24.125.63 |
35.6411.02 |
19.697.46 |
71.1330.50 |
| Gemma 4 E2B |
35.8715.34 |
46.2323.47 |
23.769.13 |
27.478.99 |
36.1513.93 |
20.7210.15 |
60.8726.35 |
| Whisper Large v3 |
36.8617.21 |
55.9634.62 |
17.835.74 |
24.667.24 |
34.6312.89 |
16.267.74 |
71.8135.04 |
Link to the live leaderboard: [Open Universal Arabic ASR Leaderboard](https://huggingface.co/spaces/elmresearchcenter/open_universal_arabic_asr_leaderboard).
## Resources
For more details and results:
* [Technical blog post](https://huggingface.co/blog/CohereLabs/cohere-transcribe-arabic-07-2026-release) contains WERs and other quality metrics.
* [Announcement blog post](https://cohere.com/blog/transcribe-arabic) for more information about the model.
* The [Open Universal Arabic ASR Leaderboard](https://huggingface.co/spaces/elmresearchcenter/open_universal_arabic_asr_leaderboard).
## Strengths and Limitations
### Strengths
Cohere Transcribe Arabic demonstrates strong transcription accuracy for Arabic and English. As a dedicated speech recognition model, it benefits from efficient inference via the Conformer encoder-decoder architecture.
### Limitations
* **Single language.** The model performs best when remaining in-distribution of a single, pre-specified language. It does not feature explicit, automatic language detection and exhibits inconsistent performance on code-switched audio.
* **Timestamps/Speaker diarization.** The model does not feature either of these.
* **Silence.** Like most AED speech models, Cohere Transcribe Arabic is eager to transcribe, even non-speech sounds. The model benefits from prepending a noise gate or VAD (voice activity detection) model in order to prevent low-volume, floor noise from turning into hallucinations.
## Model Card Contact
For errors or additional questions about details in this model card, contact [labs@cohere.com](mailto:labs@cohere.com) or raise an issue.
Terms of Use:
We hope that the release of this model will make community-based research efforts into Arabic speech more accessible. This model is governed by an Apache 2.0 license.
### Citation
To cite this model please use the following bibtex:
```bibtex
@misc{shaun_cassini_2026,
author = { Shaun Cassini and Sebastian Vincent and Xiaolu Lu and Julian Mack and Dhruti Joshi and Pierre Richemond },
title = { cohere-transcribe-arabic-07-2026 (Revision 0a8193c) },
year = 2026,
url = { https://huggingface.co/CohereLabs/cohere-transcribe-arabic-07-2026 },
doi = { 10.57967/hf/9549 },
publisher = { Hugging Face }
}
```