Edit model card

Whisper_Small_tw_nan_tw

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6855
  • Wer: 116.0558

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: 2
  • 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
0.781 0.9116 1000 0.8459 134.2798
0.4095 1.8232 2000 0.7155 121.6830
0.1653 2.7347 3000 0.6736 116.5720
0.0385 3.6463 4000 0.6855 116.0558

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
1
Safetensors
Model size
242M params
Tensor type
F32
·

Finetuned from

Dataset used to train kevin888835/whisper-small-nan-tw

Evaluation results