Ubuntu
Initial commit
9f94fb4
metadata
license: apache-2.0
base_model: duytran3112/whisper-sm-vivos
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-vietnamese-2
    results: []

whisper-vietnamese-2

This model is a fine-tuned version of duytran3112/whisper-sm-vivos on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4398
  • Wer: 15.4165
  • Cer: 8.2906

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: 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: 500
  • training_steps: 4000

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.1394 2.87 1000 0.3392 15.8696 8.6357
0.0182 5.73 2000 0.3863 15.6521 8.2710
0.008 8.6 3000 0.4126 15.2042 8.2426
0.0052 11.46 4000 0.4398 15.4165 8.2906

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.0
  • Datasets 2.14.4
  • Tokenizers 0.13.3