Med-Whisper-AfroRad-FR

Whisper Small FR - Radiologie

This model is a fine-tuned version of leduckhai/MultiMed-ST/asr/whisper-small-french on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0488
• Wer: 7.5491

Model Description

The model focuses on two main adaptations:

1. Acoustic Adaptation: Capturing the phonetic nuances of French-speaking African regions to improve recognition of local accents.
2. Medical Terminology: Stabilizing technical radiology terms (Spine, Shoulder, Thorax, Mammography, CT scans) in a dictation context.

It uses LoRA (Low-Rank Adaptation) via the adapters library, specifically targeting the first 4 layers of the Encoder (for acoustic/accent adaptation) and the full Decoder (for medical jargon and linguistic structure).

Training and Evaluation Data

• Training Dataset: ~4.5 hours of specialized radiology recordings (562 audios).

<!-- - **Segmentation Strategy**: To handle audios longer than Whisper's 30s limit, we used: - Segment Duration: 25 seconds - Overlap: 5 seconds - Proportional text-to-audio alignment. -->

Intended uses & limitations

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 12
• eval_batch_size: 8
• seed: 3407
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Performance on the Test Set

The model was evaluated on the AfroRadVoice-FR test split (75 audio files, independent of training), using identical decoding settings (temperature = 0.0) across all models for a fair comparison.

Framework versions

• Transformers 4.51.3
• Pytorch 2.8.0+cu126
• Datasets 4.4.2
• Tokenizers 0.21.4

Citation

If you use this model in your research, please cite:

@misc{med-whisper-afrorad-fr,
  author = {StephaneBah},
  title = {Med-Whisper-AfroRad-FR: Medical Radiology ASR for Afro-French Context},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\\url{https://huggingface.co/StephaneBah/Med-Whisper-AfroRad-FR}}