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: 0.7189
  • Wer: 94.7594

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.143 5.0251 1000 0.5439 109.9784
0.0159 10.0503 2000 0.6498 93.6172
0.0059 15.0754 3000 0.7012 100.0188
0.0045 20.1005 4000 0.7189 94.7594

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.20.3
Downloads last month
17
Safetensors
Model size
37.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for CheeLi03/whisper-tiny-pt-puct-4k

Finetuned
(380)
this model

Evaluation results