golesheed/whisper-non-native-adult-0-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: 0.4621
• Wer: 17.7714

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
0.7903	0.55	30	0.4799	21.8700
0.3838	1.09	60	0.4107	18.9081
0.2236	1.64	90	0.4067	28.0179
0.1796	2.18	120	0.4097	21.1335
0.1006	2.73	150	0.4123	17.6593
0.0671	3.27	180	0.4287	18.7960
0.04	3.82	210	0.4426	18.5239
0.0242	4.36	240	0.4586	18.0275
0.017	4.91	270	0.4621	17.7714

Framework versions

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