StephaneBah/whisper-small-rad-FR3

Whisper Small FR - Radiologie

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

• Loss: 1.2151
• Wer: 50.5180

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 8
• eval_batch_size: 6
• seed: 3407
• optimizer: Use OptimizerNames.ADAMW_8BIT 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

Training Loss	Epoch	Step	Validation Loss	Wer
No log	6.25	100	1.3961	111.2127
No log	12.5	200	1.2598	53.5040
No log	18.75	300	1.2146	67.8854
No log	25.0	400	1.2144	50.5180
0.262	31.25	500	1.2287	57.8915
0.262	37.5	600	1.2258	62.8275
0.262	43.75	700	1.2176	53.8087
0.262	50.0	800	1.2204	52.5289
0.262	56.25	900	1.2156	53.1383
0.0079	62.5	1000	1.2151	50.5180

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2