whisper-small-SplitEndMovie

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

• Loss: 0.9753
• Cer: 23.5657
• Wer: 38.6392

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-06
• train_batch_size: 4
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
0.8164	1.0	2620	0.7881	34.9387	55.4173
0.5435	2.0	5240	0.7639	29.3675	48.3657
0.3796	3.0	7860	0.7789	27.2382	43.7783
0.2621	4.0	10480	0.8139	25.8186	41.7910
0.1822	5.0	13100	0.8588	24.1368	39.4903
0.1278	6.0	15720	0.9034	25.3257	40.1683
0.0927	7.0	18340	0.9459	24.0187	39.2986
0.0718	8.0	20960	0.9753	23.5657	38.6392

Framework versions

• Transformers 4.56.1
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.22.0