names-whisper-en-spectrogram-vanilla

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0402
• Ner percent: 97.9270
• Wer: 1.0079

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Ner percent	Wer
0.0037	5.0251	1000	0.0355	98.5904	0.9814
0.0006	10.0503	2000	0.0369	97.6783	0.9847
0.0003	15.0754	3000	0.0386	97.6783	0.9947
0.0002	20.1005	4000	0.0397	97.9270	1.0079
0.0002	25.1256	5000	0.0402	97.9270	1.0079

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1