whipser-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: 0.5848
• Wer: 302.5

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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.072	15.38	200	0.5236	128.5
0.0005	30.77	400	0.5438	216.0
0.0002	46.15	600	0.5696	204.0
0.0001	61.54	800	0.5810	294.5
0.0001	76.92	1000	0.5848	302.5

Framework versions

• Transformers 4.29.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3