metadata

language:
  - ko
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: openai/whisper-large-v2
datasets:
  - Bingsu/zeroth-korean
model-index:
  - name: Whisper large-v2 Korean - ML_project_custom_data_2_with200
    results: []

Whisper large-v2 Korean - ML_project_custom_data_2_with200

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.5132
Cer: 92.0406

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: 0.001
train_batch_size: 4
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
No log	1.0	40	0.5362	85.7748
No log	2.0	80	0.5132	92.0406

Framework versions

PEFT 0.11.2.dev0
Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1