gonznm/whisper-small-es

Whisper Small Spanish - gonznm

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset (Spanish partition). It achieves the following results on the evaluation set:

• Loss: 0.2240
• Wer: 13.4804

Model description

Quick test.

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
0.2693	0.0454	1000	0.2640	16.0419
0.2345	0.0907	2000	0.2450	14.6287
0.2419	0.1361	3000	0.2318	14.1723
0.2184	0.1815	4000	0.2240	13.4804

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1