metadata

language:
  - ko
license: apache-2.0
base_model: openai/whisper-large
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - gingercake01/0528_1000freetalksamplewithnoise
model-index:
  - name: largeWhisper_finetuned_with_noise
    results: []

largeWhisper_finetuned_with_noise

This model is a fine-tuned version of openai/whisper-large on the 1000freetalksample dataset.

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3

Training results

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1