README.md

metadata

language:
  - ru
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - fleurs
metrics:
  - wer
model-index:
  - name: Whisper Tiny Rus - Chee Li
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: ru_ru
          split: None
          args: 'config: ru split: test'
        metrics:
          - name: Wer
            type: wer
            value: 75.21378941742384

Whisper Tiny Rus - Chee Li

This model is a fine-tuned version of openai/whisper-tiny on the Google Fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.6000
• Wer: 75.2138

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
0.1479	5.4645	1000	0.4968	79.2090
0.0266	10.9290	2000	0.5468	83.7386
0.0087	16.3934	3000	0.5872	75.7215
0.0066	21.8579	4000	0.6000	75.2138

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1