UDA-LIDI-Whisper-large-ECU-911

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

• Loss: 0.9390
• Wer: 41.2253

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7405	1.0	91	0.6308	44.1897
0.3613	2.0	182	0.6133	39.8814
0.1901	3.0	273	0.6772	39.4664
0.0998	4.0	364	0.7300	41.0672
0.0567	5.0	455	0.7617	40.6917
0.0386	6.0	546	0.8190	41.4032
0.0283	7.0	637	0.8305	40.2767
0.0219	8.0	728	0.8507	39.8617
0.0185	9.0	819	0.8770	43.2411
0.0179	9.8950	900	0.9390	41.2253

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0