CheeLi03's picture
Upload tokenizer
f816470 verified
metadata
base_model: openai/whisper-large-v3
datasets:
  - google/fleurs
language:
  - ar
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Large V3 tr finetuned 3 - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: google/fleurs
          config: ar_eg
          split: None
          args: 'config: ar split: test'
        metrics:
          - type: wer
            value: 497.6687116564417
            name: Wer

Whisper Large V3 tr finetuned 3 - Chee Li

This model is a fine-tuned version of openai/whisper-large-v3 on the Google Fleurs dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2954
  • Wer: 497.6687

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
0.0075 6.6667 1000 0.2375 284.7117
0.0015 13.3333 2000 0.2613 384.6258
0.0001 20.0 3000 0.2883 500.4663
0.0001 26.6667 4000 0.2954 497.6687

Framework versions

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