juancopi81/whisper-small-dv

Whisper Small Dv - Juan Carlos Pineros HF Class

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2937
• Wer Ortho: 56.7101
• Wer: 11.1190

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.1203	1.63	500	0.1687	62.7551	13.3724
0.0464	3.26	1000	0.1757	58.8899	12.0997
0.0327	4.89	1500	0.1931	59.0919	11.8510
0.0118	6.51	2000	0.2349	58.2492	11.4042
0.007	8.14	2500	0.2606	57.7408	11.5259
0.0056	9.77	3000	0.2759	57.4413	11.0564
0.0038	11.4	3500	0.2785	57.2185	10.9956
0.0039	13.03	4000	0.2937	56.7101	11.1190

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3