whisper-Franko-CS-v1-transcription

• Loss: 0.0774
• Wer: 28.6617
• Wer Normalized: 17.8759
• Cer: 10.7949
• Cer Normalized: 7.9230

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 6
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.15.2
• Transformers 4.52.4
• Pytorch 2.7.1+cu128
• Datasets 3.6.0
• Tokenizers 0.21.1