whisper_final

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9410
• Wer: 70.3762

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: 4
• 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: 200
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.033	2.2026	500	0.7808	70.9248
0.0058	4.4053	1000	0.8736	71.2047
0.0008	6.6079	1500	0.9240	70.6337
0.0002	8.8106	2000	0.9410	70.3762

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1