new_model

This model is a fine-tuned version of openai/whisper-medium on the telephone dataset. It achieves the following results on the evaluation set:

• Loss: 0.6867
• Cer: 6.4516

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: 4
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0	333.3333	1000	0.5950	6.4516
0.0	666.6667	2000	0.6432	6.4516
0.0	1000.0	3000	0.6765	6.4516
0.0	1333.3333	4000	0.6867	6.4516

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1