Miamoto/whisper-base-pt-muavic-duae

Whisper Base PT MUAVIC-DUAE

This model is a fine-tuned version of openai/whisper-base on the MUAVIC-DUAE dataset. It achieves the following results on the evaluation set:

• Loss: 0.3338
• Wer: 21.4148

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 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
0.4479	0.1539	1000	0.4516	27.3081
0.3887	0.3077	2000	0.4007	26.2716
0.3704	0.4616	3000	0.3603	22.9341
0.3621	0.6155	4000	0.3439	23.0858
0.3157	0.7693	5000	0.3338	21.4148

Framework versions

• Transformers 4.48.2
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0