Edit model card

Whisper Tiny Chinese

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_11_0 zh-CN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6121
  • Wer: 91.0934

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: 64
  • eval_batch_size: 32
  • 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
0.9397 2.02 1000 0.6568 98.7326
0.5387 4.04 2000 0.6149 94.5197
0.3317 6.06 3000 0.6080 95.0354
0.225 8.07 4000 0.6121 91.0934
0.3166 11.0 5000 0.6092 92.3171

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
3
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.

Dataset used to train arun100/whisper-tiny-zh-der-1

Evaluation results