pxaudio_ja_model

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: 0.4151
• Wer: 781.0535

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
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3548	1.46	1000	0.4264	207.7824
0.2464	2.91	2000	0.4010	406.9152
0.1319	4.37	3000	0.4091	637.1775
0.1065	5.82	4000	0.4151	781.0535

Framework versions

• Transformers 4.33.3
• Pytorch 2.2.0+cu118
• Datasets 2.16.1
• Tokenizers 0.13.3