ap-ja97IuW3zvwnDUEj5IelLW

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6470
• Model Preparation Time: 0.0248
• Wer: 0.1928

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• 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
• lr_scheduler_warmup_steps: 400
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer
0.3208	0.9846	40	0.4014	0.0248	0.1457
0.2262	1.9846	80	0.4377	0.0248	0.1705
0.1326	2.9846	120	0.5307	0.0248	0.1654
0.1118	3.9846	160	0.5804	0.0248	0.1829
0.1216	4.9846	200	0.6470	0.0248	0.1928

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0