metadata

license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
model-index:
  - name: whisper-medium-luganda
    results: []
datasets:
  - mozilla-foundation/common_voice_16_1
  - google/fleurs
language:
  - lg
pipeline_tag: automatic-speech-recognition

whisper-medium-luganda

This model is a fine-tuned version of openai/whisper-medium on the None dataset.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
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: 11000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2