whisper_final / README.md
RecCode's picture
Update README.md
46dc872 verified
|
raw
history blame
2.34 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
base_model: openai/whisper-large-v3
model-index:
  - name: whisper_final
    results: []

ꡬ음μž₯μ•  ν™˜μžλ₯Ό μœ„ν•œ μŒμ„±μΈμ‹ λͺ¨λΈ

곡λͺ¨μ „

  • μž¬λ‹¨λ²•μΈ λ―Έλž˜μ™€ μ†Œν”„νŠΈμ›¨μ–΄μ™€ ν•¨κ»˜ν•˜λŠ” 제 3νšŒμ•„μ΄λ””μ–΄ 곡λͺ¨μ „

ν”„λ‘œμ νŠΈ

  • "ꡬ음μž₯μ•  μŒμ„± 데이터λ₯Ό ν™œμš©ν•œ κ³ λ Ή ν™˜μžμ˜ μ˜μ‚¬μ†Œν†΅ κ°œμ„ λ°©μ•ˆ"

Model description

λ³Έ λͺ¨λΈμ€ "ꡬ음μž₯μ•  μŒμ„± 데이터λ₯Ό ν™œμš©ν•œ κ³ λ Ή ν™˜μžμ˜ μ˜μ‚¬μ†Œν†΅ κ°œμ„ λ°©μ•ˆ" ν”„λ‘œμ νŠΈμ˜ ꡬ음μž₯μ• ν™˜μžμ— λŒ€ν•œ ν•œκ΅­μ–΄ μŒμ„±μΈμ‹ λͺ¨λΈμž„. OpenAI의 Whisper λͺ¨λΈμ„ νŒŒμΈνŠœλ‹ ν•˜μ—¬ ꡬ음μž₯μ• μ˜ μŒμ„±μ  νŠΉμ„±μ„ λ°˜μ˜ν•œ λͺ¨λΈμ„ κ΅¬μΆ•ν•˜μ˜€μŒ.

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: 5e-07
  • train_batch_size: 8
  • 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: 10
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
4.2932 0.09 10 4.6306 16.0442
4.2744 0.18 20 4.1942 16.2348
3.7418 0.27 30 3.7625 15.5107
3.2037 0.36 40 3.5635 14.6723
3.4714 0.45 50 3.4383 14.3674
2.8962 0.55 60 3.3494 14.1768
2.7958 0.64 70 3.2752 18.2927
2.8691 0.73 80 3.2208 19.5884
2.8693 0.82 90 3.1857 20.6174
2.9474 0.91 100 3.1644 20.6555
3.1712 1.0 110 3.1551 20.6174

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1