translate_captions.py

import pandas as pd
from easynmt import EasyNMT

#read csv
split_0 = pd.read_csv("/content/drive/MyDrive/datasets/Image-Captioning-ACL/splits_0")
#turn that into list
split_0_captions = split_0['caption'].tolist()

#load the mbart50 english to many model
model = EasyNMT('mbart50_en2m')

split_0_tamil_captions = []
for translations in model.translate_stream(split_0_captions, show_progress_bar=True, chunk_size=16, target_lang='ta'):
    split_0_tamil_captions.append(translations)

split_0['tamil_captions'] = split_0_tamil_captions
split_0.to_csv("/content/drive/MyDrive/datasets/Image-Captioning-ACL/split_0_tamil_captions.csv")