BerB2000/whisper-small-nl-last

Whisper small nl last, Berb2000-GPU

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1789
• Wer: 307.7065

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
0.151	0.39	1000	0.2196	89.8038
0.1237	0.78	2000	0.1978	46.0495
0.044	1.17	3000	0.1840	114.0796
0.0385	1.56	4000	0.1789	307.7065

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2