whisper_go

This model is a fine-tuned version of openai/whisper-small on the go_dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.3608
• Wer: 190.5437

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: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0369	4.71	1000	0.2629	76.9137
0.0015	9.41	2000	0.3291	110.8992
0.0018	14.12	3000	0.3530	181.1038
0.0006	18.82	4000	0.3608	190.5437

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2