README.md

metadata

language:
  - uz
license: apache-2.0
base_model: openai/whisper-small
tags:
  - uz-asr-leaderboard
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small uz common voice
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice
          type: common_voice_11_0
          config: uz
          split: None
          args: 'config: tr, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 44.16791190024737

Whisper Small uz common voice

This model is a fine-tuned on the Common Voice dataset. It achieves the following results on the evaluation set:

• Loss: 0.4867
• Wer: 44.1679

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7832	0.13	500	0.7033	58.2757
0.6095	0.27	1000	0.5239	46.5073
0.5093	0.4	1500	0.4867	44.1679

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2