whisper-small-vi / README.md
stevehoang9's picture
update model card README.md
0816d69
metadata
language:
  - vi
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - JRHuy/vivos-fleurs
model-index:
  - name: Whisper Small Vietnamese - Steve Hoang
    results: []

Whisper Small Vietnamese - Steve Hoang

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

  • Loss: 1.3438

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: 1.25e-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: 50
  • training_steps: 300

Training results

Training Loss Epoch Step Validation Loss
2.4238 0.11 100 2.2401
1.8787 0.21 200 1.7789
1.3912 0.32 300 1.3438

Framework versions

  • Transformers 4.30.0
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.13.3