golesheed/whisper-non-native-adult-1-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: 0.5036
• Wer: 16.6019

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
0.7555	0.55	30	0.5180	28.4626
0.3756	1.09	60	0.4488	36.3749
0.2159	1.64	90	0.4497	19.5399
0.1656	2.18	120	0.4641	17.7056
0.1021	2.73	150	0.4502	17.1926
0.0774	3.27	180	0.4692	17.0527
0.0478	3.82	210	0.4712	18.7315
0.0264	4.36	240	0.4956	17.5657
0.016	4.91	270	0.5036	16.6019

Framework versions

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