ales/whisper-small-belarusian

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Whisper Small Belarusian

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/commonvoice11_0 be dataset. It achieves the following results on the evaluation set:

• —Loss on validation: 0.0706
• —WER on validation set: 6.3672
• —WER on test set: 6.79

Source code

All the source coude is located both in:

• —GitHub repository
• —and under src folder

Code in these 2 places should be the same. GitHub is used to make development and training of multiple models (small, base, etc.) easier.

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: 0.0001
• —trainbatchsize: 64
• —evalbatchsize: 64
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 12000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

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