whisper-10hrs-class-seed333

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

• Loss: 0.3586
• Wer: 17.4489

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: 0.0001
• train_batch_size: 48
• eval_batch_size: 32
• seed: 42
• 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: 26
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8806	0.2955	26	0.9285	34.2973
0.4181	0.5909	52	0.4614	19.8678
0.4246	0.8864	78	0.4047	18.6533
0.4063	1.1818	104	0.3876	18.0729
0.3575	1.4773	130	0.3752	17.8381
0.3587	1.7727	156	0.3681	18.4688
0.3334	2.0682	182	0.3634	18.1333
0.3513	2.3636	208	0.3626	17.9555
0.3256	2.6591	234	0.3594	17.7743
0.3371	2.9545	260	0.3586	17.4489

Framework versions

• PEFT 0.16.0
• Transformers 4.57.3
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.22.2