mikr/whisper-small-sk-cv11

Whisper Small Slovak

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

• Loss: 0.6225
• Wer: 33.8172

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
0.0038	14.0	1000	0.5366	34.2575
0.0006	28.01	2000	0.5914	34.8881
0.0003	42.01	3000	0.6225	33.8172
0.0002	57.0	4000	0.6411	34.1385
0.0002	71.01	5000	0.6498	34.0195

Framework versions

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