mangoo111/repo_name

AIHub_non-face-to-face-care_data_model

This model is a fine-tuned version of openai/whisper-base on the AIHub_non-face-to-face-care_data dataset. It achieves the following results on the evaluation set:

• Loss: 0.5251
• Cer: 91.7452
• Normalized Cer: 0.1147

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	Normalized Cer
0.6825	2.5	1000	0.7206	125.5376	0.1569
0.4637	5.0	2000	0.4858	96.4728	0.1206
0.34	7.5	3000	0.4926	92.8792	0.1161
0.2378	10.0	4000	0.5251	91.7452	0.1147

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1