js886io/Diplomovka
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Jakub Schwarc 2026-08-20 22:59:57 +02:00
parent 6962418bb1
commit 20bcf01be7
2 changed files with 2 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
README.md
View File

Binary file not shown.

15
strojovy_preklad/translate_dataset_to_slovak.py
View File

@ -6,10 +6,6 @@ from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# -----------------------------
# Nastavenia
# -----------------------------
DATASET_NAME = "tatsu-lab/alpaca" DATASET_NAME = "tatsu-lab/alpaca"
SPLIT = "train" SPLIT = "train"
@ -41,10 +37,7 @@ def is_empty(value):
def load_already_done(path): def load_already_done(path):
"""
Ak skript spadne alebo ho zastavíš, vie pokračovať.
Načíta už preložené riadky.
"""
if not path.exists(): if not path.exists():
return [] return []
@ -58,10 +51,7 @@ def load_already_done(path):
def translate_batch(texts, tokenizer, model, device): def translate_batch(texts, tokenizer, model, device):
"""
Preloží batch textov z angličtiny do slovenčiny.
Prázdne texty nechá prázdne.
"""
results = [""] * len(texts) results = [""] * len(texts)
non_empty_indices = [] non_empty_indices = []
@ -108,7 +98,6 @@ def translate_batch(texts, tokenizer, model, device):
return results return results
# Main
def main(): def main():
print("Loading dataset...") print("Loading dataset...")