whisper-small-hi

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: 0.1700
• Wer: 19.3327

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
0.0006	9.52	1000	0.1495	18.6304
0.0002	19.05	2000	0.1598	32.0983
0.0001	28.57	3000	0.1674	19.9649
0.0001	38.1	4000	0.1700	19.3327

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.14.1