PaidDatasetsBad/whisper-small-test

Whisper Small Refined

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8921
• Wer: 15.3846

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-08
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 250
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0045	400.0	400	0.9209	30.7692
0.0008	800.0	800	0.8990	15.3846
0.0003	1200.0	1200	0.8957	15.3846
0.0002	1600.0	1600	0.8931	15.3846
0.0001	2000.0	2000	0.8927	15.3846
0.0001	2400.0	2400	0.8927	15.3846
0.0001	2800.0	2800	0.8919	15.3846
0.0001	3200.0	3200	0.8912	15.3846
0.0001	3600.0	3600	0.8918	15.3846
0.0001	4000.0	4000	0.8921	15.3846

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.0
• Datasets 2.19.1
• Tokenizers 0.19.1