handler.py

from typing import Dict, Any
import logging
import torch
import soundfile as sf
from transformers import AutoTokenizer, AutoModelForTextToWaveform

# Configure logging
logging.basicConfig(level=logging.DEBUG)
# Configure logging
logging.basicConfig(level=logging.ERROR)
# Configure logging
logging.basicConfig(level=logging.WARNING)



class CustomHandler:
    def __init__(self):
        
        self.tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
        self.model= AutoModelForTextToWaveform.from_pretrained("facebook/mms-tts-eng")
    def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
        # Prepare the payload with input data
        logging.warning(f"------input_data-- {str(data)}")
        payload = str(data)
        logging.warning(f"payload----{str(payload)}")
        # Set headers with API token
        inputs = self.tokenizer(payload, return_tensors="pt")

        # Generate the waveform from the input text
        with torch.no_grad():
            outputs = self.model(**inputs)

        # Save the audio to a file
        sf.write("StoryAudio.wav", outputs["waveform"][0].numpy(), self.model.config.sampling_rate)
        
        return 'StoryAudio.wav'
        # Check if the request was successful