whisper-medium-test

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

• Loss: 0.3629
• Wer: 99.9968

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: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2455	1.14	400	0.3382	99.9925
0.1461	2.27	800	0.3414	99.9925
0.0878	3.41	1200	0.3629	99.9968

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.0
• Tokenizers 0.12.1