metadata

base_model: openai/whisper-base
datasets:
  - fleurs
language:
  - pt
library_name: transformers
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Base Portugese Punctuation 5k - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: pt_br
          split: None
          args: 'config: pt split: test'
        metrics:
          - type: wer
            value: 34.92197781537883
            name: Wer

Whisper Base Portugese Punctuation 5k - Chee Li

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

Loss: 0.5540
Wer: 34.9220

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0508	5.0251	1000	0.4118	56.8105
0.0041	10.0503	2000	0.4887	45.7558
0.0019	15.0754	3000	0.5250	38.7902
0.0012	20.1005	4000	0.5450	34.5742
0.001	25.1256	5000	0.5540	34.9220

Framework versions

Transformers 4.46.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.20.3