whisper_medium_ptt

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: 0.9243
• Cer: 20.6774

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
0.0001	71.43	1000	0.8405	21.2121
0.0	142.86	2000	0.8907	20.4991
0.0	214.29	3000	0.9152	20.6774
0.0	285.71	4000	0.9243	20.6774

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2