pratyush_whisper_tiny_finetune_teacher_clean_libri360_epochs_50_batch_16

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

• Loss: 0.2123
• Wer: 12.0749

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 512
• total_train_batch_size: 8192
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5132	12.47	150	0.2368	13.3561
0.118	24.95	300	0.2032	12.0804
0.0672	37.47	450	0.2098	12.0308
0.0538	49.95	600	0.2123	12.0749

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1
• Datasets 2.7.1
• Tokenizers 0.11.0