whisper-small-co / README.md
ntviet's picture
End of training
0cd4d76 verified
metadata
language:
  - co
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - ntviet/Co-audio-dataset
model-index:
  - name: Whisper Small Co
    results: []

Whisper Small Co

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

  • Loss: 0.0056
  • Cer Ortho: 0.0
  • Cer: 0.0

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: 50
  • training_steps: 600
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer Ortho Cer
0.0243 9.84 600 0.0056 0.0 0.0

Framework versions

  • Transformers 4.39.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2