birgermoell/whisper-small-sv-fast

Whisper Small Swedish Fast

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

• Loss: 1.8738
• Wer: 62.6922

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: 64
• eval_batch_size: 32
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.0512	6.01	1000	2.5997	87.1949
0.4367	12.02	2000	1.8089	68.1271
0.0806	18.03	3000	1.7969	63.5711
0.0194	25.01	4000	1.8435	63.4663
0.0121	31.02	5000	1.8738	62.6922

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2