CheeLi03/whisper-tiny-nl-puct-4k

Whisper Tiny Dutch Punctuation 5k - Chee Li

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

• Loss: 1.0318
• Wer: 193.0864

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2297	5.1546	1000	0.8384	125.7963
0.0387	10.3093	2000	0.9217	167.4590
0.0112	15.4639	3000	1.0067	201.5565
0.0081	20.6186	4000	1.0318	193.0864

Framework versions

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