README.md

metadata

language:
  - ru
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - aangry-mouse/stepik_ml_ru
metrics:
  - wer
model-index:
  - name: Whisper Base Ml Ru
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ML датасет
          type: aangry-mouse/stepik_ml_ru
          args: 'config: ru, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 35.272870043188064

Whisper Base Ml Ru

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

• Loss: 0.4705
• Wer: 35.2729

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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6752	0.6649	250	0.6513	39.3404
0.4415	1.3298	500	0.5277	38.4923
0.4037	1.9947	750	0.4766	35.0766
0.2825	2.6596	1000	0.4705	35.2729

Framework versions

• Transformers 4.41.0
• Pytorch 2.0.1+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1