whisper_finetune

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

• Loss: 0.4617
• Cer: 0.1788

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
• training_steps: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.5098	0.2273	5	0.4941	0.1674
0.4481	0.4545	10	0.4709	0.1764
0.4681	0.6818	15	0.4636	0.1802
0.4641	0.9091	20	0.4617	0.1788

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1