second2

This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2553
• eval_cer: 3.9437
• eval_wer: 13.3115
• eval_bleu: 0.7447
• eval_runtime: 981.1698
• eval_samples_per_second: 0.936
• eval_steps_per_second: 0.234
• epoch: 0.96
• step: 4500

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: 8
• eval_batch_size: 4
• seed: 420
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• training_steps: 10500
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.52.0
• Pytorch 2.9.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.4