GerwinVanGiessen/whisper-base-nl

Whisper Base NL

This model is a fine-tuned version of openai/whisper-base on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3354
• Wer: 20.4818

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.294	0.3734	1000	0.4016	24.5123
0.216	0.7468	2000	0.3617	22.3141
0.1437	1.1202	3000	0.3424	21.1733
0.1299	1.4937	4000	0.3354	20.4818

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1