CheeLi03's picture
Upload tokenizer
bcc1e88 verified
metadata
base_model: openai/whisper-large-v3
datasets:
  - fleurs
language:
  - pl
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Large V3 pl preprocessed - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: pl_pl
          split: None
          args: 'config: pl split: test'
        metrics:
          - type: wer
            value: 340.8656818962556
            name: Wer

Whisper Large V3 pl preprocessed - 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: 0.1210
  • Wer: 340.8657

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: 250
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0131 2.5126 500 0.1070 30.9447
0.001 5.0251 1000 0.1158 186.2041
0.0011 7.5377 1500 0.1201 375.3281
0.0002 10.0503 2000 0.1210 340.8657

Framework versions

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