README.md

metadata

language:
  - pt
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Large V3 pt Fleurs Aug - Chee Li
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Google Fleurs
          type: google/fleurs
          config: pt_br
          split: None
          args: 'config: pt split: test'
        metrics:
          - name: Wer
            type: wer
            value: 418.6592073715387

Whisper Large V3 pt 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: 0.1648
• Wer: 418.6592

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: 5e-06
• 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
0.0298	1.2579	1000	0.1279	73.4662
0.0053	2.5157	2000	0.1516	315.7726
0.0058	3.7736	3000	0.1560	433.2424
0.0005	5.0314	4000	0.1648	418.6592

Framework versions

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