job_1_whisper-20250719_183755-sw

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: 1.1627
• Score Wer: 1.0
• Score Cer: 1.0

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• 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: cosine
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Score Wer	Score Cer
0.3892	5.0	500	0.8385	1.0	1.0
0.0424	10.0	1000	0.9497	1.0	1.0
0.0093	15.0	1500	1.0384	1.0	1.0
0.0026	20.0	2000	1.0717	1.0	1.0
0.0012	25.0	2500	1.1105	1.0	1.0
0.0003	30.0	3000	1.1357	1.0	1.0
0.0003	35.0	3500	1.1509	1.0	1.0
0.0002	40.0	4000	1.1591	1.0	1.0
0.0002	45.0	4500	1.1627	1.0	1.0

Framework versions

• Transformers 4.53.2
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.2