whisper-torgo

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

• eval_loss: 0.0657
• eval_wer: 0.0827
• eval_cer: 0.0518
• eval_f1: 0.9403
• eval_runtime: 317.9979
• eval_samples_per_second: 2.83
• eval_steps_per_second: 0.355
• epoch: 0.1975
• step: 100

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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: 3000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.1.1
• Tokenizers 0.21.2