|
|
|
--- |
|
language: ko |
|
tags: |
|
- whisper |
|
- speech-recognition |
|
datasets: |
|
- maxseats/aihub-464-preprocessed-680GB-set-0 |
|
metrics: |
|
- cer |
|
--- |
|
# Model Name : SungBeom/whisper-small-ko |
|
# Description |
|
|
|
- νμΈνλ λ°μ΄ν°μ
: maxseats/aihub-464-preprocessed-680GB-set-0 |
|
- AI hubμ μ£Όμ μμλ³ νμ μμ± λ°μ΄ν°μ
680GB μ€ μ²«λ²μ§Έ λ°μ΄ν°(10GB)λ₯Ό νμΈνλν λͺ¨λΈμ
λλ€. |
|
- λ°μ΄ν°μ
λ§ν¬ : https://huggingface.co/datasets/maxseats/aihub-464-preprocessed-680GB-set-0 |
|
|
|
# νλΌλ―Έν° |
|
|
|
``` |
|
model_name = "SungBeom/whisper-small-ko" # λμ : "SungBeom/whisper-small-ko" |
|
dataset_name = "maxseats/aihub-464-preprocessed-680GB-set-0" # λΆλ¬μ¬ λ°μ΄ν°μ
(νκΉ
νμ΄μ€ κΈ°μ€) |
|
|
|
CACHE_DIR = '/mnt/a/maxseats/.finetuning_cache' # μΊμ λλ ν 리 μ§μ |
|
is_test = False # True: μλμ μν λ°μ΄ν°λ‘ ν
μ€νΈ, False: μ€μ νμΈνλ |
|
|
|
token = "hf_" # νκΉ
νμ΄μ€ ν ν° μ
λ ₯ |
|
|
|
training_args = Seq2SeqTrainingArguments( |
|
output_dir=model_dir, # μνλ 리ν¬μ§ν 리 μ΄λ¦μ μ
λ ₯νλ€. |
|
per_device_train_batch_size=16, |
|
gradient_accumulation_steps=2, # λ°°μΉ ν¬κΈ°κ° 2λ°° κ°μν λλ§λ€ 2λ°°μ© μ¦κ° |
|
learning_rate=1e-5, |
|
warmup_steps=1000, |
|
# max_steps=2, # epoch λμ μ€μ |
|
num_train_epochs=1, # epoch μ μ€μ / max_stepsμ μ΄κ² μ€ νλλ§ μ€μ |
|
gradient_checkpointing=True, |
|
fp16=True, |
|
evaluation_strategy="steps", |
|
per_device_eval_batch_size=16, |
|
predict_with_generate=True, |
|
generation_max_length=225, |
|
save_steps=1000, |
|
eval_steps=1000, |
|
logging_steps=25, |
|
report_to=["tensorboard"], |
|
load_best_model_at_end=True, |
|
metric_for_best_model="cer", # νκ΅μ΄μ κ²½μ° 'wer'보λ€λ 'cer'μ΄ λ μ ν©ν κ² |
|
greater_is_better=False, |
|
push_to_hub=True, |
|
save_total_limit=5, # μ΅λ μ μ₯ν λͺ¨λΈ μ μ§μ |
|
) |
|
``` |
|
|