rishabhjain16/whisper_small_en_to_myst55h

openai/whisper-small.en

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

• Loss: 0.5806
• Wer: 12.9802

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: 64
• eval_batch_size: 32
• 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: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1886	2.01	500	0.3621	11.9972
0.187	4.03	1000	0.3786	12.3615
0.0285	6.04	1500	0.4436	12.5951
0.0319	8.06	2000	0.5057	12.8262
0.0044	10.07	2500	0.5620	13.1238
0.0054	13.01	3000	0.5806	12.9802

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.9.1.dev0
• Tokenizers 0.13.2