README.md

metadata

language:
  - he
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
base_model: openai/whisper-medium
model-index:
  - name: Whisper Medium Hebrew
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: google/fleurs he_il
          type: google/fleurs
          config: he_il
          split: test
          args: he_il
        metrics:
          - type: wer
            value: 34
            name: Wer

Whisper Medium Hebrew

This model is a fine-tuned version of openai/whisper-medium on the google/fleurs he_il dataset. It achieves the following results on the evaluation set:

• Wer: 34

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: 32
• eval_batch_size: 32
• 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: 5000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2