Edit model card

Whisper large-v2 nan-tw

This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 nan-tw dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7525
  • Wer: 42.5930
  • Cer: 23.2970

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: 2
  • 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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.4781 1.04 1000 0.7256 52.4690 28.7583
0.1881 2.08 2000 0.7346 50.2067 26.6389
0.0429 3.13 3000 0.7094 45.3557 24.7811
0.0112 5.01 4000 0.7416 44.4203 24.6850
0.0011 6.05 5000 0.7525 42.5930 23.2970

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
9
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 thomas0104/whisper_large_v2_nan_tw

Finetuned
(183)
this model

Dataset used to train thomas0104/whisper_large_v2_nan_tw

Evaluation results

  • Wer on mozilla-foundation/common_voice_11_0 nan-tw
    self-reported
    42.593
  • Cer on mozilla-foundation/common_voice_11_0 nan-tw
    self-reported
    23.297