Hugging Face's logo

lazio1900
/
ft-whisper_jb

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ft-whisper_jb / README.md
lazio1900's picture
lazio1900
End of training
0606034 verified
preview code
|
raw
history blame contribute delete
1.29 kB
metadata
library_name: transformers
language:
  - ko
license: apache-2.0
base_model: openai/whisper-base
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - lazio1900/stt_test
model-index:
  - name: lazio1900
    results: []

lazio1900

This model is a fine-tuned version of openai/whisper-base on the lazio1900 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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • training_steps: 100
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.47.0.dev0
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3