whisper-turbo-pato-02

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2515
• Wer: 25.6664
• Wer Ortho: 26.8311

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 7.0

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Wer Ortho
0.4437	1.0	459	0.3643	41.9650	46.3404
0.1951	2.0	918	0.2703	29.8553	26.6582
0.1158	3.0	1377	0.2621	19.4212	21.8533
0.0839	4.0	1836	0.2435	18.1264	20.1398
0.0543	5.0	2295	0.2488	19.9543	21.8660
0.0416	6.0	2754	0.2556	23.9147	25.1684
0.0233	7.0	3213	0.2515	25.6664	26.8311

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.1+cu124
• Datasets 3.0.1
• Tokenizers 0.20.0