whisper-tiny-ja-test

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

• Loss: 0.6032
• Wer: 85.7143

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: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• training_steps: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.7501	3.33	10	1.6891	42.8571
0.6513	6.67	20	0.4518	85.7143
0.0104	10.0	30	0.5347	85.7143
0.0006	13.33	40	0.6032	85.7143

Framework versions

• Transformers 4.33.2
• Pytorch 2.1.1+cu118
• Datasets 2.16.1
• Tokenizers 0.13.3