whisper-medium-cantonese

This model is a fine-tuned version of openai/whisper-medium on the thisiskeithkwan/canto dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7006
  • Cer: 3.6111

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: 32
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss Cer
0.6458 0.76 500 0.7109 3.5960
0.4183 1.52 1000 0.7006 3.6111

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.3
  • Tokenizers 0.13.3
Downloads last month
23
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 thisiskeithkwan/whisper-medium-1000steps

Finetuned
(498)
this model