CheeLi03/whisper-base-nl-puct-5k

Whisper Base Dutch Punctuation 5k - Chee Li

This model is a fine-tuned version of openai/whisper-base on the Google Fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.8128
• Wer: 54.4402

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
0.0633	5.1546	1000	0.6299	49.1433
0.0055	10.3093	2000	0.7255	43.7379
0.0025	15.4639	3000	0.7736	45.1014
0.0017	20.6186	4000	0.8005	50.4585
0.0014	25.7732	5000	0.8128	54.4402

Framework versions

• Transformers 4.46.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.20.3