whisper-tiny-paper

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6807
• Wer: 50.8558

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: 2e-05
• train_batch_size: 48
• eval_batch_size: 48
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	72	0.6515	50.3886
No log	2.0	144	0.6566	50.8012
No log	3.0	216	0.6624	50.3713
No log	4.0	288	0.6684	50.8026
No log	5.0	360	0.6807	50.8558

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.7.0
• Tokenizers 0.13.3