metadata

library_name: transformers
language:
  - kk
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper Small Kk - Kazakh
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17.0
          type: mozilla-foundation/common_voice_17_0
          config: kk
          split: None
          args: 'config: kk, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 46.14655716993051

Whisper Small Kk - Kazakh

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.6964
Wer: 46.1466

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
0.0018	15.1515	1000	0.6017	49.5578
0.0002	30.3030	2000	0.6563	46.5572
0.0001	45.4545	3000	0.6854	46.1150
0.0001	60.6061	4000	0.6964	46.1466

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu118
Datasets 3.3.2
Tokenizers 0.21.0