Cristhian2430/whisper-large-coes-v7

Whisper Large SEIN - COES SEIN - Version 7

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

• Loss: 2.7602
• Wer: 58.0711

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: 16
• eval_batch_size: 8
• 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0267	83.3333	500	2.2424	60.1015
0.0013	166.6667	1000	2.5216	59.6954
0.0001	250.0	1500	2.6548	59.3909
0.0001	333.3333	2000	2.6880	58.8832
0.0001	416.6667	2500	2.7241	58.7817
0.0	500.0	3000	2.7435	58.3756
0.0	583.3333	3500	2.7557	58.2741
0.0	666.6667	4000	2.7602	58.0711

Framework versions

• Transformers 4.56.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4