golesheed/whisper-v2-Zeelandic

Whisper Large V2

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6750
• Wer: 28.0120

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: 3e-05
• train_batch_size: 12
• 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: 20
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0702	0.7895	15	0.5925	27.5691
0.0715	1.5789	30	0.6284	36.0383
0.0686	2.3684	45	0.6231	26.2580
0.0454	3.1579	60	0.6415	25.3721
0.0225	3.9474	75	0.6376	24.6102
0.011	4.7368	90	0.6750	28.0120

Framework versions

• Transformers 4.44.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1