Update app.py

app.py

@@ -2,24 +2,20 @@ import whisper
 import gradio as gr
 from groq import Groq
 from deep_translator import GoogleTranslator
-from diffusers import StableDiffusionPipeline
-import os
-import torch
-import openai
-from huggingface_hub import InferenceApi
 from PIL import Image
+import os
 import requests
 import io
 import time
 
 # Set up Groq API key
-api_key = os.getenv("gkannada_key")
+api_key = os.getenv("GROQ_API_KEY")
 client = Groq(api_key=api_key)
 
 # Hugging Face API details for image generation
-key = os.getenv("h_key")
+H_key = os.getenv("Hugging_api_key")
 API_URL = "https://api-inference.huggingface.co/models/Artples/LAI-ImageGeneration-vSDXL-2"
-headers = {"Authorization": f"Bearer {key}"}
+headers = {"Authorization": f"Bearer {H_key}"}
 
 # Function for querying image generation with retries
 def query_image_generation(payload, max_retries=5):
@@ -28,4 +24,102 @@ def query_image_generation(payload, max_retries=5):
 
         if response.status_code == 503:
             print(f"Model is still loading, retrying... Attempt {attempt + 1}/{max_retries}")
-            estimated_time = min(response.json().get("estimated_time", 60), 6
+            estimated_time = min(response.json().get("estimated_time", 60), 60)
+            time.sleep(estimated_time)
+            continue
+
+        if response.status_code != 200:
+            print(f"Error: Received status code {response.status_code}")
+            print(f"Response: {response.text}")
+            return None
+
+        return response.content
+
+    print(f"Failed to generate image after {max_retries} attempts.")
+    return None
+
+# Function for generating an image from text
+def generate_image(prompt):
+    image_bytes = query_image_generation({"inputs": prompt})
+
+    if image_bytes is None:
+        return None
+
+    try:
+        image = Image.open(io.BytesIO(image_bytes))  # Opening the image from bytes
+        return image
+    except Exception as e:
+        print(f"Error: {e}")
+        return None
+
+# Updated function for text generation using the new API structure
+def generate_creative_text(prompt):
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {"role": "user", "content": prompt}
+        ],
+        model="llama-3.2-90b-text-preview"
+    )
+    chatbot_response = chat_completion.choices[0].message.content
+    return chatbot_response
+
+def process_audio(audio_path, image_option, creative_text_option):
+    if audio_path is None:
+        return "Please upload an audio file.", None, None, None
+
+    # Step 1: Transcribe audio
+    try:
+        with open(audio_path, "rb") as file:
+            transcription = client.audio.transcriptions.create(
+                file=(os.path.basename(audio_path), file.read()),
+                model="whisper-large-v3",
+                language="kn",  # Change to Kannada
+                response_format="verbose_json",
+            )
+        kannada_text = transcription.text  # Changed from tamil_text to kannada_text
+    except Exception as e:
+        return f"An error occurred during transcription: {str(e)}", None, None, None
+
+    # Step 2: Translate Kannada to English
+    try:
+        translator = GoogleTranslator(source='kn', target='en')
+        translation = translator.translate(kannada_text)  # Changed from tamil_text to kannada_text
+    except Exception as e:
+        return kannada_text, f"An error occurred during translation: {str(e)}", None, None
+
+    # Step 3: Generate creative text (if selected)
+    creative_text = None
+    if creative_text_option == "Generate Creative Text":
+        creative_text = generate_creative_text(translation)
+
+    # Step 4: Generate image (if selected)
+    image = None
+    if image_option == "Generate Image":
+        image = generate_image(translation)
+        if image is None:
+            return kannada_text, translation, creative_text, "An error occurred during image generation."
+
+    return kannada_text, translation, creative_text, image      
+
+# Create Gradio interface
+with gr.Blocks(theme=gr.themes.Base()) as iface:
+    gr.Markdown("# Audio Transcription, Translation, Image & Creative Text Generation")
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(type="filepath", label="Upload Audio File")
+            image_option = gr.Dropdown(["Generate Image", "Skip Image"], label="Image Generation", value="Generate Image")
+            creative_text_option = gr.Dropdown(["Generate Creative Text", "Skip Creative Text"], label="Creative Text Generation", value="Generate Creative Text")
+            submit_button = gr.Button("Process Audio")
+        with gr.Column():
+            kannada_text_output = gr.Textbox(label="Kannada Transcription")  # Changed to Kannada
+            translation_output = gr.Textbox(label="English Translation")
+            creative_text_output = gr.Textbox(label="Creative Text")
+            image_output = gr.Image(label="Generated Image")
+    submit_button.click(
+        fn=process_audio,
+        inputs=[audio_input, image_option, creative_text_option],
+        outputs=[kannada_text_output, translation_output, creative_text_output, image_output]
+    )
+
+# Launch the interface
+iface.launch()