rishabhjain16/whisper_large_v2_to_myst55h

openai/whisper-large-v2

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3834
• Wer: 11.8889

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: 16
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5582	0.12	500	0.3660	14.8170
0.2285	1.02	1000	0.2919	12.6304
0.2038	1.15	1500	0.2795	11.3850
0.074	2.04	2000	0.3150	12.1043
0.2165	2.17	2500	0.2978	12.8510
0.0399	3.07	3000	0.3467	11.7322
0.045	3.19	3500	0.3501	11.7218
0.0187	4.09	4000	0.3834	11.8889

Framework versions

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