whisper-tiny-withnoise

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

• Loss: 0.2688
• Cer: 50.6208

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: 8
• 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	Cer
0.0002	500.0	1000	0.2156	35.2436
0.0002	1000.0	2000	0.2518	41.5473
0.0001	1500.0	3000	0.2638	40.5922
0.0001	2000.0	4000	0.2688	50.6208

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1