Hugging Face's logo

daftenp
/
whisper-tiny-foreign-speech-korean

Automatic Speech Recognition
Transformers
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Community
whisper-tiny-foreign-speech-korean / README.md
daftenp's picture
daftenp
Upload processor
f7519cf verified
preview code
|
raw
history blame contribute delete
1.35 kB
metadata
base_model: openai/whisper-tiny
datasets:
  - daftenp/foreign_speech_korean_data
language:
  - ko
library_name: transformers
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: foreign_speech_korean_transcribe
    results: []

foreign_speech_korean_transcribe

This model is a fine-tuned version of openai/whisper-tiny on the foreign_speech_korean_data 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: 8
  • 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: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.46.0.dev0
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.0