whisper-medium-toigen-baseline-model

This model is a fine-tuned version of openai/whisper-medium on the toigen dataset. It achieves the following results on the evaluation set:

• Loss: 0.6728
• Wer: 0.4726

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.8705	1.6260	200	0.7698	0.5497
0.75	3.2520	400	0.6728	0.4726
0.5272	4.8780	600	0.6986	0.4247
0.1709	6.5041	800	0.7418	0.4874
0.1112	8.1301	1000	0.7826	0.4230

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0