whisper-small-ko-normalized-1273h

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1426
• Wer: 0.0671

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: 32
• 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: 100
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0726	1.0	6581	0.1490	0.0721
0.0368	2.0	13162	0.1405	0.0686
0.0317	3.0	19743	0.1426	0.0671

Framework versions

• Transformers 4.28.0.dev0

• Pytorch 1.13.1+cu117

• Datasets 2.11.0

• Tokenizers 0.13.2

• Evaluation Result for the dataset google/fleurs

The trained model is evaluated on the test split of subset ko_kr from the dataset google/fleurs. Please note that the model was not trained on the train split from the dataset.

model	Wer
openai/whisper	0.2826
this model	0.2679