File size: 1,771 Bytes
93e1cee 8b7a347 93e1cee 25a6de1 3b456ab 93e1cee 8601dd4 1a8704e 93e1cee 25a6de1 93e1cee 25a6de1 93e1cee 25a6de1 93e1cee 25a6de1 93e1cee | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | import os
import asyncio
import torch
import streamlit as st
from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
from transformers import MBart50Tokenizer
os.environ["STREAMLIT_WATCH_FILE_SYSTEM"] = "false"
try:
asyncio.get_running_loop()
except RuntimeError:
asyncio.set_event_loop(asyncio.new_event_loop())
# Load model and tokenizer
model_path = "app90/ChhattishgarhiAI_Model"
model = MBartForConditionalGeneration.from_pretrained(model_path)
tokenizer = MBart50Tokenizer.from_pretrained(model_path, src_lang="hi_IN", tgt_lang="hne_IN")
tokenizer.save_pretrained("CG_AI")
# Translate Hindi → Chhattisgarhi
def translate_hindi_to_chhattisgarhi(text):
sentences = text.split("।")
translated_sentences = []
for sentence in sentences:
sentence = sentence.strip()
if sentence:
inputs = tokenizer(sentence, return_tensors="pt", truncation=True, padding="longest", max_length=256)
with torch.no_grad():
translated_ids = model.generate(**inputs, max_length=256, num_beams=5, early_stopping=True)
translated_text = tokenizer.decode(translated_ids[0], skip_special_tokens=True)
translated_sentences.append(translated_text)
return " । ".join(translated_sentences)
# Streamlit UI
st.title("Hindi to Chhattisgarhi Translator 🗣️")
st.write("Enter a Hindi sentence and get its translation in Chhattisgarhi.")
user_input = st.text_area("Enter text:")
if st.button("Translate"):
if user_input.strip():
chhattisgarhi_text = translate_hindi_to_chhattisgarhi(user_input)
st.success(f"**Chhattisgarhi Translation**:\n{chhattisgarhi_text}")
else:
st.warning("⚠ Please enter some text before translating.")
|