cohere-transcribe-darija

Cohere Transcribe — Moroccan Darija (hybrid)

Public adapter on Cohere Transcribe Arabic. Hybrid: MultiConv on encoder layers 15–47 + LoRA on the decoder. Trained on 3h YouTube Darija (01Yassine/darija-asr-3h).

Eval: atlasia/darija-asr-benchmark (114 clips, human).

You need the Cohere base weights (and its license). This repo is only the adapter.

Inference (from the Hub, no training clone)

pip install "transformers>=5.4" peft torch torchaudio soundfile huggingface_hub

from huggingface_hub import snapshot_download
import sys
sys.path.insert(0, snapshot_download("01Yassine/cohere-transcribe-darija"))
from infer import transcribe
print(transcribe("clip.wav"))

Or, if you already have infer.py from this repo:

python infer.py clip.wav --model hybrid
python infer.py clip.wav --model 01Yassine/cohere-transcribe-darija

Other open checkpoints

Same data and seed, different trainable slice:

print(transcribe("clip.wav", model_id="full_lora"))
print(transcribe("clip.wav", model_id="01Yassine/cohere-transcribe-darija-encoder-lora"))