names-whisper-en-spectrogram-pitch-shifted

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: 0.2429
• Wer: 5.4494

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	Wer
0.0362	5.0251	1000	0.2300	7.0812
0.0012	10.0503	2000	0.2335	5.4763
0.0005	15.0754	3000	0.2378	5.3453
0.0003	20.1005	4000	0.2413	5.4058
0.0003	25.1256	5000	0.2429	5.4494

Framework versions

• Transformers 4.40.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1