Modelpublic

01Yassine/cohere-transcribe-darija

sourceHugging Faceotherupdated 26d agoView on Hugging Face

0likes41downloads

Model Card

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).

	CER	WER
base	20.2	49.1
hybrid (this repo)	14.4	38.3

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

Inference (from the Hub, no training clone)

bash

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

python

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:

bash

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:

recipe	Hub	AtlasIA CER
hybrid (MultiConv + LoRA)	`01Yassine/cohere-transcribe-darija`	14.4
full LoRA	`01Yassine/cohere-transcribe-darija-full-lora`	16.5
encoder LoRA	`01Yassine/cohere-transcribe-darija-encoder-lora`	17.4
decoder LoRA	`01Yassine/cohere-transcribe-darija-decoder-lora`	20.2

python

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