whisper-base-fr

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

• eval_loss: 0.5471
• eval_model_preparation_time: 0.0029
• eval_wer: 0.2782
• eval_cer: 0.1415
• eval_runtime: 206.3542
• eval_samples_per_second: 2.481
• eval_steps_per_second: 0.31
• epoch: 0.2844
• step: 9385

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: 5e-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• 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: 33000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1