whisper-small-canario_orto

This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4499
• Wer: 91.6524

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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
0.1319	5.38	1000	0.9796	89.6131
0.0373	10.75	2000	1.2377	90.0133
0.0213	16.13	3000	1.4101	92.6434
0.0133	21.51	4000	1.4499	91.6524

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Tokenizers 0.15.0