README.md

metadata

language:
  - hu
license: apache-2.0
tags:
  - generated_from_trainer
base_model: openai/whisper-tiny
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small En - Benedek Borbely
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: hu
          split: test
          args: 'config: hu, split: test'
        metrics:
          - type: wer
            value: 71.2272672528002
            name: Wer

Whisper Small En - Benedek Borbely

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

• Loss: 0.8894
• Wer: 71.2273

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• 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: 50
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8364	0.54	400	0.8894	71.2273

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.14.5
• Tokenizers 0.15.2