whisper_large_finetune_Formosa

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

  • Loss: 0.1572
  • Wer: 9.8143

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: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2883 0.1018 500 0.1850 13.1693
0.2687 0.2035 1000 0.1702 10.7376
0.2417 0.3053 1500 0.1626 10.1341
0.2628 0.4070 2000 0.1572 9.8143

Framework versions

  • Transformers 4.41.2
  • Pytorch 1.13.1+cu116
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
22
Safetensors
Model size
1.54B params
Tensor type
F32
·
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 Alexlinander/whisper-large-ch

Finetuned
(53)
this model