whisperasr

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: 32
• 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: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.102	0.18	50	1.1915	62.8450
0.0958	0.36	100	1.1914	83.6518
0.1058	0.55	150	1.1923	75.0531
0.1103	0.73	200	1.2138	75.2654

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.0.1
• Datasets 2.14.6
• Tokenizers 0.14.1