pyton , languange transfer , to transflate telugu text to english text.

 

enable language transfer google service, better

format file, with help paragaph wise in notepad++;  crcd. \r\n. when paragraph ends.

generate in blogspot. languange transfer. copy the content, looks easy then below.

--

!pip show google-cloud-translate

import os

from google.oauth2 import service_account

from google.cloud import translate_v2 as translate

# Paths to the files

credentials_path = '/content/credentials_doc.json'

input_text_file_path = '/content/Pravakthalu-Yevaru_telugu_18thsep24.txt'

output_text_file_path = '/content/Pravakthalu-Yevaru_English_18thsep24.txt'

# Verify the file existence

if os.path.exists(credentials_path):

    print("Credentials file found.")

else:

    print("Credentials file not found. Please check the path.")

if os.path.exists(input_text_file_path):

    print("Input text file found.")

else:

    print("Input text file not found. Please check the path.")

# Authenticate using service account

credentials = service_account.Credentials.from_service_account_file(credentials_path)

# Initialize the translation client

translate_client = translate.Client(credentials=credentials)

# Function to translate text from Telugu to English

def translate_text(text, target_language='en'):

    result = translate_client.translate(text, target_language=target_language)

    return result['translatedText']

# Function to split text into chunks

def split_text(text, max_chunk_size=5000):

    # Split the text into paragraphs

    paragraphs = text.split('\n\n')  # Assuming paragraphs are separated by double newlines

    chunks = []

    current_chunk = ""

    for paragraph in paragraphs:

        # If adding the next paragraph exceeds max_chunk_size, finalize the current chunk

        if len(current_chunk) + len(paragraph) > max_chunk_size:

            chunks.append(current_chunk.strip())

            current_chunk = paragraph  # Start a new chunk with the current paragraph

        else:

            # Add the paragraph to the current chunk

            current_chunk += paragraph + "\n\n"

   

    # Add the last chunk if it's not empty

    if current_chunk.strip():

        chunks.append(current_chunk.strip())

   

    return chunks

# Read the Telugu text file

with open(input_text_file_path, 'r', encoding='utf-8') as input_file:

    telugu_text = input_file.read()

# Split the text into smaller chunks

chunks = split_text(telugu_text)

# Translate each chunk and save the translated text to the output file

with open(output_text_file_path, 'w', encoding='utf-8') as output_file:

    for i, chunk in enumerate(chunks):

        # Translate the chunk

        translated_chunk = translate_text(chunk)

        # Write the translated chunk to the output file

        output_file.write(translated_chunk)

        output_file.write("\n\n")

print(f'Translated text written to file "{output_text_file_path}"')

---