Cohere Darija LoRA 10 7 26

--- language: - ar tags: - automatic-speech-recognition - speech-to-text - darija - moroccan-arabic - peft - lora base_model: CohereLabs/cohere-transcribe-arabic-07-2026 datasets: - atlasia/DODa-audio-dataset --- # Cohere ASR - Moroccan Darija (LoRA Adapter) This model is a fine-tuned LoRA adapter for the `CohereLabs/cohere-transcribe-arabic-07-2026` Automatic Speech Recognition (ASR) model. It has been specifically trained to improve transcription accuracy for **Moroccan Darija**. ## Model Details - **Base Model:** [CohereLabs/cohere-transcribe-arabic-07-2026](https://huggingface.co/CohereLabs/cohere-transcribe-arabic-07-2026) - **Dataset:** Fine-tuned on the [atlasia/DODa-audio-dataset](https://huggingface.co/datasets/atlasia/DODa-audio-dataset) (Moroccan Darija audio samples). - **Task:** Speech-to-Text / Automatic Speech Recognition (ASR) - **Language:** Moroccan Arabic (Darija) ## Training Configuration The model was fine-tuned using Parameter-Efficient Fine-Tuning (PEFT) with LoRA and 8-bit quantization. - **Steps:** 500 - **Batch Size:** 4 (with Gradient Accumulation Steps = 4) - **Learning Rate:** 1e-4 - **Precision:** 32-bit (fp16 disabled to prevent NaN loss in the audio architecture) ## How to Use You can use this adapter by loading the base model and merging it with this LoRA repository. ```python import librosa import torch from transformers import AutoFeatureExtractor, AutoTokenizer, CohereAsrForConditionalGeneration from peft import PeftModel base_model_id = "CohereLabs/cohere-transcribe-arabic-07-2026" adapter_repo = "amzilmustapha/cohere-darija-lora-10-7-26" hf_token = "YOUR_HF_TOKEN" # Required for the gated base model # Load processors feature_extractor = AutoFeatureExtractor.from_pretrained(base_model_id, trust_remote_code=True, token=hf_token) tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True, token=hf_token) # Load base model base_model = CohereAsrForConditionalGeneration.from_pretrained( base_model_id, device_map="auto", trust_remote_code=True, token=hf_token ) # Apply LoRA Adapter model = PeftModel.from_pretrained(base_model, adapter_repo, token=hf_token) # Process Audio audio_file = "your_darija_audio.wav" audio_array, sampling_rate = librosa.load(audio_file, sr=16000) inputs = feature_extractor(audio_array, sampling_rate=16000, return_tensors="pt") input_features = inputs.input_featur...