allandclive's picture
Update README.md
11c69fe verified
metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
model-index:
  - name: whisper-tiny-lug
    results: []
language:
  - lg
datasets:
  - mozilla-foundation/common_voice_16_1
  - google/fleurs
pipeline_tag: automatic-speech-recognition

whisper-tiny-luganda

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-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: linear
  • lr_scheduler_warmup_ratio: 0.05
  • training_steps: 21000
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2