whisper-small-sv

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3178
• Wer: 112.0916

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
0.3164	0.65	500	0.3268	71.7055
0.1574	1.29	1000	0.2951	126.5010
0.1168	1.94	1500	0.2882	62.9857
0.0678	2.59	2000	0.2879	63.6175
0.0341	3.23	2500	0.2999	67.0081
0.0306	3.88	3000	0.2958	78.9842
0.0112	4.53	3500	0.3186	104.4231
0.0082	5.17	4000	0.3178	112.0916

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0