Edit model card

Whisper Large V2 Cantonese

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

  • Loss: 0.2807
  • Cer: 6.7274

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: 8
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • 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 Cer
0.0032 13.01 1000 0.2318 6.8569
0.002 26.01 2000 0.2404 7.1524
0.0001 39.02 3000 0.2807 6.7274
0.0001 53.01 4000 0.2912 6.7517
0.0 66.01 5000 0.2957 6.7638

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
1,666
Safetensors
Model size
1.54B params
Tensor type
F32
·
Hosted inference API
or or
This model can be loaded on the Inference API on-demand.

Dataset used to train simonl0909/whisper-large-v2-cantonese

Space using simonl0909/whisper-large-v2-cantonese 1

Evaluation results