metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
model-index:
  - name: ko-address-whisper-small-5e-6
    results: []

ko-address-whisper-small-5e-6

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

eval_loss: 0.0484
eval_cer: 0.9441
eval_runtime: 3023.3682
eval_samples_per_second: 3.842
eval_steps_per_second: 0.24
epoch: 0.4861
step: 2000

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: 5e-06
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_steps: 500
training_steps: 8000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.41.0.dev0
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.19.1