File size: 1,662 Bytes
bd4f7b2 1129d6c 0af51be 2734ce5 bd4f7b2 c2a94ab bd4f7b2 ce531bd 669b0a4 bd4f7b2 0af51be bd4f7b2 1129d6c 0af51be 5fa79a1 bd4f7b2 1129d6c a108533 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
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
|