dgx1_whisper_base_finetune_teacher_no_noise_mozilla_100_epochs_batch_16

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

• Loss: 0.8926
• Wer: 31.8954

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: 0.001
• train_batch_size: 16
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 256
• total_train_batch_size: 4096
• 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: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1866	29.41	500	0.8619	34.0680
1.4402	58.82	1000	0.8918	32.2505
0.0001	88.23	1500	0.8926	31.8954

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.1
• Datasets 2.8.0
• Tokenizers 0.13.2