whisper-base-Superb-3-Epochs

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3391
• Wer: 20.3876

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
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3834	1.0	169	0.3817	24.3324
0.2556	2.0	338	0.3460	20.6958
0.1832	3.0	507	0.3391	20.3876

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3