app.py

import gradio as gr
import base64
import numpy as np
from scipy.io import wavfile
from voice_processing import parallel_tts, get_model_names
import os
import logging
from rvc_service import RVCService  # Our new service
import asyncio
from voice_processing import parallel_tts, get_model_names
import sys
from datetime import datetime  # Add this import
import traceback
import json


# Set up enhanced logging
logging.basicConfig(
    level=logging.DEBUG,
    format='%(asctime)s | %(levelname)s | %(name)s | %(message)s',
    handlers=[
        logging.FileHandler('rvc_server.log'),
        logging.StreamHandler(sys.stdout)
    ]
)
logger = logging.getLogger('rvc_server')

# Initialize RVC Service
rvc_service = RVCService()

def setup_request_logging():
    """Creates a unique logger for request handling"""
    request_id = datetime.now().strftime('%Y%m%d_%H%M%S_%f')
    logger = logging.getLogger(f'request_{request_id}')
    return logger, request_id

def convert_tts(model_name, audio_file, slang_rate):
    """Voice conversion endpoint"""
    req_logger, request_id = setup_request_logging()
    
    try:
        req_logger.info(f"New request received - ID: {request_id}")
        req_logger.info(f"Parameters: model={model_name}, slang_rate={slang_rate}")
        
        if audio_file is None:
            req_logger.error("No audio file provided")
            return {"error": "No audio file uploaded."}, None

        try:
            req_logger.info(f"Processing audio file: {audio_file}")
            sr, audio = wavfile.read(audio_file)
            req_logger.info(f"Audio loaded: sr={sr}Hz, shape={audio.shape}")

            # Create task for parallel processing
            task = (model_name, None, None, slang_rate, True, audio_file)
            
            req_logger.info("Running parallel processing")
            result = parallel_tts([task])
            
            if not result or result[0] is None:
                req_logger.error("Processing failed - no result")
                return {"error": "Processing failed"}, None

            # Get the result and return directly
            result_tuple = result[0]
            
            # Check if result_tuple is in the expected format
            if isinstance(result_tuple, tuple) and len(result_tuple) == 3:
                info, _, (tgt_sr, audio_output) = result_tuple
                
                if audio_output is None:
                    req_logger.error("No audio output generated")
                    return {"error": "No audio output generated"}, None

                # Save the output
                output_filename = f"output_{request_id}.wav"
                output_path = os.path.join("outputs", output_filename)
                os.makedirs("outputs", exist_ok=True)

                if isinstance(audio_output, np.ndarray):
                    req_logger.info(f"Saving numpy array output: shape={audio_output.shape}")
                    wavfile.write(output_path, tgt_sr, audio_output)
                else:
                    req_logger.info("Saving raw audio output")
                    with open(output_path, "wb") as f:
                        f.write(audio_output)
                
                req_logger.info(f"Successfully saved to {output_path}")
                return {"info": info}, output_path
            else:
                req_logger.error(f"Invalid result format: {result_tuple}")
                return {"error": "Invalid result format"}, None

        except Exception as e:
            req_logger.error(f"Error processing audio: {str(e)}")
            return {"error": f"Processing error: {str(e)}"}, None

    except Exception as e:
        req_logger.error(f"Unexpected error: {str(e)}")
        return {"error": str(e)}, None
        
# Create the Gradio interface with queue
iface = gr.Interface(
    fn=convert_tts,  # Remove async if it's there
    inputs=[
        gr.Dropdown(choices=get_model_names(), label="Model", interactive=True),
        gr.Audio(label="Upload Audio", type="filepath"),
        gr.Slider(minimum=0, maximum=1, step=0.01, label="Slang Rate"),
    ],
    outputs=[
        gr.JSON(label="Info"),
        gr.Audio(label="Converted Audio")
    ],
    title="Voice Conversion"
).queue()

if __name__ == "__main__":
    logger.info("Starting RVC server")
    try:
        iface.launch(
            debug=True,
            show_error=True,
            max_threads=10
        )
    except Exception as e:
        logger.error(f"Error launching server: {e}", exc_info=True)