Edit model card

Whisper Small Cantanese

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2823
  • Wer: 55.5764

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • 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
0.116 1.3908 1000 0.2522 59.0687
0.0418 2.7816 2000 0.2504 57.7169
0.0065 4.1725 3000 0.2702 56.1772
0.0031 5.5633 4000 0.2823 55.5764

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
11
Safetensors
Model size
242M params
Tensor type
F32
·

Finetuned from

Dataset used to train poppysmickarlili/whisper-small-cantonese_02-05-2024-1727

Evaluation results