Whisper-Cantonese / README.md
WayneLinn's picture
add all files
2e6929c
metadata
language:
  - yue
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: Whisper Cantonese
    results: []

Whisper Cantonese

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:

  • eval_loss: 0.3030
  • eval_wer: 60.0485
  • eval_runtime: 556.4418
  • eval_samples_per_second: 4.381
  • eval_steps_per_second: 0.548
  • epoch: 5.56
  • step: 1000

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: 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

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu116
  • Datasets 2.7.1
  • Tokenizers 0.13.2