Hugging Face's logo

gcasey2
/
whisper-large-v3-ko-en-v2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-large-v3-ko-en-v2 / README.md
gcasey2's picture
gcasey2
End of training
d08b547 verified
preview code
|
raw
history blame contribute delete
1.42 kB
metadata
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
model-index:
  - name: Whisper Large Korean/English
    results: []

Whisper Large Korean/English

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.1397
  • eval_wer: 8.2666
  • eval_runtime: 6120.463
  • eval_samples_per_second: 0.827
  • eval_steps_per_second: 0.103
  • epoch: 6.0
  • step: 7590

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1265
  • training_steps: 12650
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.0.1
  • Datasets 2.17.0
  • Tokenizers 0.15.2