golesheed/whisper-non-native-adult-6-dutch

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: 0.3679
• Wer: 12.7848

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: 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: 20
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7686	0.55	30	0.3602	18.3326
0.3835	1.09	60	0.3292	15.3107
0.22	1.64	90	0.3163	16.9069
0.1668	2.18	120	0.3356	16.5194
0.0955	2.73	150	0.3383	13.4356
0.0674	3.27	180	0.3632	11.9944
0.0376	3.82	210	0.3584	12.6143
0.0218	4.36	240	0.3645	12.9242
0.0136	4.91	270	0.3679	12.7848

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.15.0