rishabhjain16/whisper_small_to_myst55h

openai/whisper-small

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

• Loss: 0.5154
• Wer: 13.4267

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
0.167	2.01	500	0.3235	13.2309
0.1796	4.03	1000	0.3410	12.8549
0.0274	6.04	1500	0.4035	13.0246
0.0305	8.06	2000	0.4462	13.4476
0.0041	10.07	2500	0.5034	13.3144
0.0046	13.01	3000	0.5154	13.4267

Framework versions

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