handler.py

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


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




class EndpointHandler():
    def __init__(self, path=""):
        
        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)
        uploadGraphFile("StoryAudio.wav")
       
        #return 'StoryAudio.wav'
        # Check if the request was successful
        
def uploadGraphFile(fileName):
    # Configure Cloudinary credentials
    cloudinary.config( 
        cloud_name = "dm9tdqvp6", 
        api_key ="793865869491345", 
        api_secret = "0vhdvBoM35IWcO29NyI04Qj1PMo" 
    )
    # Upload a file to Cloudinary
    result = cloudinary.uploader.upload(fileName, folder="poc-graph", resource_type="raw")
    return result