README.md

metadata

language:
  - pt
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - M2LabOrg/jwlang
metrics:
  - wer
model-index:
  - name: Whisper medium pt jwlang - Michel Mesquita
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: jwlang 1.0
          type: M2LabOrg/jwlang
          args: 'config: pt, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 18.727050183598532

Whisper medium pt jwlang - Michel Mesquita

This model is a fine-tuned version of openai/whisper-medium on the jwlang 1.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6361
• Wer: 18.7271

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
0.0038	14.0845	1000	0.5291	20.3182
0.0001	28.1690	2000	0.6034	18.9718
0.0	42.2535	3000	0.6277	19.0942
0.0	56.3380	4000	0.6361	18.7271

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1