whisper_small_c1

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

• Loss: 0.7706
• Cer: 15.7895

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: 16
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0	333.33	1000	0.6593	14.2857
0.0	666.67	2000	0.7241	12.0301
0.0	1000.0	3000	0.7576	15.7895
0.0	1333.33	4000	0.7706	15.7895

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.1+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0