---
language:
- ar
- fr
tags:
- whisper
- speech-recognition
- algerian-dialect
- arabic
- asr
- automatic-speech-recognition
license: apache-2.0
datasets:
- UBC-NLP/Casablanca
model-index:
- name: MohammedNasri/whisper-algerian-dialect
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: Casablanca Algeria
      type: UBC-NLP/Casablanca
      config: Algeria
      split: validation
    metrics:
    - type: wer
      value: 23.0
      name: Word Error Rate
---

# Whisper Fine-tuned for Algerian Dialect

This model is a fine-tuned version of OpenAI's Whisper-tiny specifically for Algerian dialect automatic speech recognition (ASR).

## Model Description

- **Base Model**: openai/whisper-tiny
- **Language**: Algerian Arabic dialect with French code-switching
- **Dataset**: UBC-NLP/Casablanca (Algeria subset)
- **Task**: Automatic Speech Recognition (ASR)
- **Fine-tuned by**: Mohammed Nasri

## Performance

- **Word Error Rate (WER)**: ~23% on validation set
- **Optimized for**: Algerian dialect, Arabic-French code-switching
- **Training**: Fine-tuned with low-resource optimization techniques

## Usage

```python
from transformers import WhisperForConditionalGeneration, WhisperProcessor
import torch
import numpy as np

# Load model and processor
model = WhisperForConditionalGeneration.from_pretrained("MohammedNasri/whisper-algerian-dialect")
processor = WhisperProcessor.from_pretrained("MohammedNasri/whisper-algerian-dialect")

# Process audio (audio_array should be 16kHz mono)
inputs = processor(audio_array, sampling_rate=16000, return_tensors="pt")

# Generate transcription
with torch.no_grad():
    predicted_ids = model.generate(inputs["input_features"])
    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]

print(transcription)
```

## Training Details

- **Training Framework**: HuggingFace Transformers
- **Optimization**: Mixed precision training, gradient accumulation
- **Hardware**: Optimized for both CPU and GPU training
- **Memory**: Ultra low-memory training techniques applied
- **Training Steps**: 3 steps (proof of concept)
- **Batch Size**: Minimal for memory optimization

## Dataset

The model was trained on the Algeria subset of the [UBC-NLP/Casablanca](https://huggingface.co/datasets/UBC-NLP/Casablanca) dataset, which contains authentic Algerian dialect audio recordings with transcriptions.

## Limitations

- This is a proof-of-concept model trained with minimal steps for demonstration
- For production use, longer training with more steps is recommended
- Optimized for Algerian dialect but may work with other North African Arabic dialects

## Citation

If you use this model, please cite:

```bibtex
@misc{whisper-algerian-dialect,
  title={Whisper Fine-tuned for Algerian Dialect},
  author={Mohammed Nasri},
  year={2024},
  publisher={Hugging Face},
  url={https://huggingface.co/MohammedNasri/whisper-algerian-dialect}
}
```

## Acknowledgments

- OpenAI for the Whisper model
- UBC-NLP for the Casablanca dataset
- HuggingFace for the training infrastructure