whisper-tiny-tsukuyomi

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: 0.0655
• Wer: 12.5

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
5.8824	3.33	10	5.3742	100.0
3.5587	6.67	20	1.4774	50.0
0.7316	10.0	30	0.1563	12.5
0.0253	13.33	40	0.0655	12.5

Framework versions

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