Create app.py

app.py

@@ -0,0 +1,147 @@
+import torch
+from transformers import pipeline
+import librosa
+import os
+from hugchat import hugchat
+from hugchat.login import Login
+import gradio as gr
+
+# Model and device configuration for transcription
+MODEL_NAME = "openai/whisper-large-v3-turbo"
+device = 0 if torch.cuda.is_available() else "cpu"
+
+# Initialize Whisper pipeline
+pipe = pipeline(
+    task="automatic-speech-recognition",
+    model=MODEL_NAME,
+    chunk_length_s=30,
+    device=device,
+)
+
+# Hugging Face Chatbot credentials (use environment variables in production)
+EMAIL = "fearfreed007@gmail.com"  # Replace with your email or use secure methods
+PASSWD = "uS&m?UrB)7Y7XTP"  # Replace with your password or use secure methods
+
+# Directory to save cookies
+cookie_path_dir = "./cookies/"
+os.makedirs(cookie_path_dir, exist_ok=True)
+
+# Log in and initialize chatbot
+sign = Login(EMAIL, PASSWD)
+cookies = sign.login(cookie_dir_path=cookie_path_dir, save_cookies=True)
+chatbot = hugchat.ChatBot(cookies=cookies.get_dict())
+
+def transcribe_audio(audio_path):
+    """
+    Transcribe a local audio file using the Whisper pipeline.
+    """
+    try:
+        audio, sr = librosa.load(audio_path, sr=16000, mono=True)
+        transcription = pipe(audio, batch_size=8, generate_kwargs={"language": "urdu"})["text"]
+        return transcription
+    except Exception as e:
+        return f"Error processing audio: {e}"
+
+def extract_info_from_filename(filename):
+    """
+    Extract agent, file_number, city, and country from the filename.
+    Example: 'agent1_2_Multan_Pakistan' -> agent='agent1', file_number=2, city='Multan', country='Pakistan'
+    """
+    try:
+        parts = filename.split('_')
+        if len(parts) >= 4:
+            agent = parts[0]
+            file_number = int(parts[1])
+            city = parts[2]
+            country = parts[3].split('.')[0]  # Remove file extension if present
+            return agent, file_number, city, country
+        else:
+            raise ValueError("Filename format incorrect")
+    except Exception as e:
+        return None, None, None, None
+
+def process_audio(audio_path):
+    """
+    Process audio: Extract info from filename, transcribe, and generate JSON via chatbot.
+    """
+    # Save filename and extract info
+    filename = os.path.basename(audio_path)
+    agent, file_number, city, country = extract_info_from_filename(filename)
+    
+    if agent is None:
+        return '{"error": "Invalid filename format. Use format: agentX_N_City_Country.wav"}', "", ""
+
+    # Transcribe audio
+    transcription = transcribe_audio(audio_path)
+    if "Error" in transcription:
+        return f'{{"error": "{transcription}"}}', transcription, ""
+
+    # Construct prompt with extracted data
+    prompt = f"""
+    Correct the given Urdu text for grammar, word accuracy, and contextual meaning without adding anything extra. 
+    Then, translate the corrected text into English.
+
+    Next, create a JSON file that detects crops and their diseases, following this format:
+    {{
+      "records": [
+        {{
+          "Recording_name": "{filename}",
+          "agent": "{agent}",
+          "file_number": {file_number},
+          "city": "{city}",
+          "country": "{country}",
+          "crops": [
+            {{
+              "name": "<detected_crop>",
+              "season": "<appropriate_season>",
+              "harvest_months": ["<months>"],
+              "regions": ["<regions>"],
+              "diseases": [
+                {{
+                  "name": "<disease>",
+                  "description": "<description>",
+                  "wikipedia_link": "<link>"
+                }}
+              ]
+            }}
+          ],
+          "issues": ["<detected_issues>"],
+          "disease_linking": {{
+            "<crop_name>": ["<disease_names>"]
+          }}
+        }}
+      ]
+    }}
+
+    The Urdu text to process is:
+    {transcription}
+
+    Only provide the JSON output, do not include any additional text.
+    """
+
+    # Process with chatbot and return JSON
+    response = chatbot.chat(prompt).wait_until_done()
+    return response, transcription, filename
+
+# Gradio Interface
+with gr.Blocks(title="Audio Transcription and Crop Analysis") as interface:
+    gr.Markdown("## Audio Transcription and Crop Disease Analysis")
+    
+    with gr.Row():
+        audio_input = gr.Audio(type="filepath", label="Upload Audio File (e.g., agent1_2_Multan_Pakistan.wav)")
+    
+    with gr.Row():
+        json_output = gr.Textbox(label="JSON Output", interactive=False)
+        transcription_output = gr.Textbox(label="Transcription (Urdu)", interactive=False)
+        filename_output = gr.Textbox(label="Processed Filename", interactive=False)
+    
+    process_button = gr.Button("Process Audio")
+
+    process_button.click(
+        fn=process_audio,
+        inputs=[audio_input],
+        outputs=[json_output, transcription_output, filename_output],
+    )
+
+if __name__ == "__main__":
+    interface.launch()