README.md

metadata

language:
  - ru
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_0
metrics:
  - wer
model-index:
  - name: Whisper Base Ru
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.0
          type: mozilla-foundation/common_voice_16_0
          config: ru
          split: None
          args: 'config: ru, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 151.55619160645514

Whisper Base Ru

This model is a fine-tuned version of openai/whisper-base on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3411
• Wer: 151.5562

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
0.3519	0.61	1000	0.3882	155.8949
0.2055	1.21	2000	0.3565	159.1748
0.2047	1.82	3000	0.3422	164.2338
0.1469	2.43	4000	0.3411	151.5562

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.2
• Datasets 2.18.0
• Tokenizers 0.15.1