liqi03's picture
Upload tokenizer
0871408 verified
metadata
base_model: openai/whisper-large-v3
datasets:
  - google/fleurs
language:
  - pl
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Large V3 pl Fleurs Aug - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: google/fleurs
          config: pl_pl
          split: None
          args: 'config: pl split: test'
        metrics:
          - type: wer
            value: 281.1154598825832
            name: Wer

Whisper Large V3 pl Fleurs Aug - 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: 0.1225
  • Wer: 281.1155

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
0.0502 1.2579 1000 0.1122 224.0774
0.0099 2.5157 2000 0.1146 344.2200
0.0033 3.7736 3000 0.1187 283.3869
0.0005 5.0314 4000 0.1225 281.1155

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1