ap-Dpm3ZXosNY0Ubz2hhBrTFH

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2013
• Model Preparation Time: 0.0103
• Wer: 3.33%

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.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: 400
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer
0.4992	1.0	2	2.0320	0.0103	3.33%
1.38	2.0	4	1.5284	0.0103	3.33%
1.019	3.0	6	0.9962	0.0103	3.33%
0.637	4.0	8	0.3020	0.0103	0.00%
0.2666	5.0	10	0.2013	0.0103	3.33%

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.2