johnatanebonilla/whisper-small-canario

Whisper Small Canario - Johnatan E. Bonilla

This model is a fine-tuned version of openai/whisper-small on the COSER Canario 1.0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.2760
• Wer: 86.4808

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
0.3041	3.95	1000	0.8140	104.0241
0.0471	7.91	2000	1.0680	109.6910
0.0238	11.86	3000	1.2071	92.1929
0.013	15.81	4000	1.2760	86.4808

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Tokenizers 0.15.0