names-whisper-en-spectrogram-original

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: 0.1720
• Ner percent: 105.0286
• Wer: 5.9900

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
0.0081	5.1546	1000	0.1413	104.8314	5.9866
0.0017	10.3093	2000	0.1528	104.7256	5.8949
0.0007	15.4639	3000	0.1628	105.3074	5.9764
0.0005	20.6186	4000	0.1690	104.9219	5.9764
0.0004	25.7732	5000	0.1720	105.0286	5.9900

Framework versions

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