whisper-large-v3-nyagen-balanced-model

This model is a fine-tuned version of openai/whisper-large-v3 on the nyagen dataset. It achieves the following results on the evaluation set:

• Loss: 0.3155
• Wer: 0.2403

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.426	1.0756	200	0.4108	0.3070
0.6798	2.1511	400	0.3343	0.2867
0.3574	3.2267	600	0.3155	0.2403
0.2691	4.3023	800	0.3365	0.2158
0.1851	5.3779	1000	0.3159	0.2904
0.0715	6.4534	1200	0.3676	0.2084

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0