Spaces:
Runtime error
Runtime error
File size: 3,178 Bytes
37409eb 1a79b75 8f4f20a 37409eb 1a79b75 572127c 3782eb8 85152a6 3782eb8 85152a6 1a79b75 85152a6 3782eb8 85152a6 3782eb8 85152a6 37409eb 85152a6 1a79b75 790888c 3782eb8 790888c 3782eb8 790888c 3782eb8 85152a6 790888c 85152a6 1a79b75 85152a6 1a79b75 85152a6 1a79b75 37409eb d0fda9d |
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 75 76 |
from transformers import MBartForConditionalGeneration, MBart50Tokenizer
import gradio as gr
import requests
import io
from PIL import Image
import os
import time
# Load the translation model and tokenizer
model_name = "facebook/mbart-large-50-many-to-one-mmt"
tokenizer = MBart50Tokenizer.from_pretrained(model_name)
model = MBartForConditionalGeneration.from_pretrained(model_name)
# Use the Hugging Face API key from environment variables for text-to-image model
hf_api_key = os.getenv("full_token")
if hf_api_key is None:
raise ValueError("Hugging Face API key not found! Please set 'full_token' environment variable.")
else:
headers = {"Authorization": f"Bearer {hf_api_key}"}
# Define the text-to-image model URL (using a stable diffusion model)
API_URL = "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4"
# Function to generate an image using Hugging Face's text-to-image model
def generate_image_from_text(translated_text):
try:
print(f"Generating image from translated text: {translated_text}")
response = requests.post(API_URL, headers=headers, json={"inputs": translated_text})
# Check if the response is successful
if response.status_code != 200:
print(f"Error generating image: {response.text}")
return None, f"Error generating image: {response.text}"
# Read and return the generated image
image_bytes = response.content
image = Image.open(io.BytesIO(image_bytes))
print("Image generation completed.")
return image, None
except Exception as e:
print(f"Error during image generation: {e}")
return None, f"Error during image generation: {e}"
# Define the function to translate Tamil text and generate an image
def translate_and_generate_image(tamil_text):
# Step 1: Translate Tamil text to English using mbart-large-50
try:
print("Translating Tamil text to English...")
tokenizer.src_lang = "ta_IN"
inputs = tokenizer(tamil_text, return_tensors="pt")
translated_tokens = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["en_XX"])
translated_text = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
print(f"Translation completed: {translated_text}")
except Exception as e:
return f"Error during translation: {e}", None
# Step 2: Directly generate an image using the translated English text
image, error_message = generate_image_from_text(translated_text)
if error_message:
return translated_text, error_message
return translated_text, image
# Gradio interface setup
iface = gr.Interface(
fn=translate_and_generate_image,
inputs=gr.Textbox(lines=2, placeholder="Enter Tamil text here..."),
outputs=[gr.Textbox(label="Translated English Text"),
gr.Image(label="Generated Image")],
title="Tamil to English Translation and Image Creation",
description="Translate Tamil text to English using Facebook's mbart-large-50 model and create an image using the translated text.",
)
# Launch Gradio app without `share=True`
iface.launch()
|