whisper-small-hy

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

• Loss: 0.2581
• Wer: 40.8397

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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2078	1.77	1000	0.2089	45.6217
0.0948	3.54	2000	0.2087	41.2060
0.0453	5.31	3000	0.2385	40.9550
0.0315	7.08	4000	0.2581	40.8397

Framework versions

• Transformers 4.26.1
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.13.3