whisper-small-hy

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5691
• Wer: 74.7706

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 125
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1258	4.1	250	0.3914	76.0813
0.0064	8.2	500	0.4882	74.5740
0.0008	12.3	750	0.5486	74.2464
0.0007	16.39	1000	0.5691	74.7706

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0