File size: 3,099 Bytes
bf7e1be 5a6cf02 52b96f9 87884fb 2bd9593 87884fb 2c77ef8 87884fb 2bd9593 87884fb bf7e1be 2c77ef8 bf7e1be 2bd9593 bf7e1be 2c77ef8 2bd9593 bf7e1be 2bd9593 52b96f9 bf7e1be 2bd9593 bf7e1be 2bd9593 52b96f9 2bd9593 bf7e1be 2bd9593 52b96f9 bf7e1be 2bd9593 bf7e1be 2bd9593 52b96f9 2bd9593 bf7e1be 2bd9593 2c77ef8 2bd9593 52b96f9 2bd9593 2c77ef8 2bd9593 2c77ef8 2bd9593 2c77ef8 |
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 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
import gradio as gr
import requests
from transformers import MarianMTModel, MarianTokenizer, AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import torch
import io
import os
from typing import Tuple
# Load Hugging Face token
HF_API_KEY = os.getenv("HF_API_KEY") or "your_hf_token_here"
if not HF_API_KEY:
raise ValueError("HF_API_KEY is not set.")
# Hugging Face inference API endpoint
IMAGE_GEN_URL = "https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-schnell"
HEADERS = {"Authorization": f"Bearer {HF_API_KEY}"}
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Translation model (Tamil to English)
translator_model = "Helsinki-NLP/opus-mt-mul-en"
translator_tokenizer = MarianTokenizer.from_pretrained(translator_model)
translator = MarianMTModel.from_pretrained(translator_model).to(device)
# Text generation model
text_model = "EleutherAI/gpt-neo-1.3B"
text_tokenizer = AutoTokenizer.from_pretrained(text_model)
text_generator = AutoModelForCausalLM.from_pretrained(text_model).to(device)
text_tokenizer.pad_token = text_tokenizer.eos_token
# Step 1: Tamil to English translation
def translate_tamil_to_english(text: str) -> str:
inputs = translator_tokenizer(text, return_tensors="pt", padding=True, truncation=True).to(device)
outputs = translator.generate(**inputs)
return translator_tokenizer.decode(outputs[0], skip_special_tokens=True)
# Step 2: Generate creative text
def generate_text(prompt: str) -> str:
inputs = text_tokenizer(prompt, return_tensors="pt", padding=True, truncation=True).to(device)
outputs = text_generator.generate(**inputs, max_length=100, num_return_sequences=1)
return text_tokenizer.decode(outputs[0], skip_special_tokens=True)
# Step 3: Generate image
def generate_image(prompt: str) -> Image.Image:
response = requests.post(IMAGE_GEN_URL, headers=HEADERS, json={"inputs": prompt})
if response.status_code == 200 and response.headers.get("content-type", "").startswith("image"):
return Image.open(io.BytesIO(response.content))
else:
return Image.new("RGB", (512, 512), color="gray")
# Master function
def process_input(tamil_text: str) -> Tuple[str, str, Image.Image]:
english = translate_tamil_to_english(tamil_text)
creative = generate_text(english)
image = generate_image(english)
return english, creative, image
# Gradio UI using Blocks API
with gr.Blocks() as demo:
gr.Markdown("## 🌍 Tamil to English | Text & Image Generator")
with gr.Row():
tamil_input = gr.Textbox(label="📝 Enter Tamil Text", placeholder="உங்கள் உரையை இங்கே உள்ளிடவும்...", lines=2)
generate_btn = gr.Button("Translate & Generate")
english_output = gr.Textbox(label="🇬🇧 Translated English")
creative_output = gr.Textbox(label="✨ Generated Text")
image_output = gr.Image(label="🖼️ Generated Image", type="pil")
generate_btn.click(fn=process_input, inputs=tamil_input, outputs=[english_output, creative_output, image_output])
demo.launch()
|