names-whisper-en

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: 0.0544
• Wer: 1.9975

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
0.0722	0.8757	1000	0.0689	2.3877
0.0287	1.7513	2000	0.0569	2.0774
0.0134	2.6270	3000	0.0541	2.0056
0.0084	3.5026	4000	0.0536	2.0440
0.0053	4.3783	5000	0.0544	1.9975

Framework versions

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