rishabhjain16/whisper_medium_en_to_myst_pf

openai/whisper-medium.en

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

• Loss: 0.4522
• Wer: 10.7946

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: 32
• 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
0.2652	0.12	500	0.3042	11.2277
0.2102	1.11	1000	0.2824	10.9156
0.1913	2.1	1500	0.2924	11.2366
0.0249	3.09	2000	0.3386	10.6246
0.031	4.07	2500	0.3798	11.1400
0.0224	5.06	3000	0.4086	10.9767
0.0033	6.05	3500	0.4452	10.3392
0.0028	7.03	4000	0.4522	10.7946

Framework versions

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