metadata

library_name: transformers
language:
  - ru
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Ru other
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: ru
          split: test
          args: 'config: ru, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 15.34873498095145

Whisper Small Ru other

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2081
Wer: 15.3487

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
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
0.178	0.9479	1000	0.1979	16.3720
0.0963	1.8957	2000	0.1937	15.7016
0.0279	2.8436	3000	0.2003	15.2364
0.015	3.7915	4000	0.2081	15.3487

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu124
Datasets 3.0.1
Tokenizers 0.20.0