from ultralytics import YOLO
from base64 import b64encode
from speech_recognition import AudioFile, Recognizer
import numpy as np
from scipy.spatial import distance as dist

from sahi.utils.cv import read_image_as_pil
from fastapi import FastAPI, File, UploadFile, Form
from utils import tts, read_image_file, pil_to_base64, base64_to_pil, get_hist
from typing import Optional
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="ultralyticsplus/yolov8s", filename='yolov8s.pt')
model = YOLO(model_path)
CLASS = model.model.names
defaul_bot_voice = "おはいようございます"
area_thres = 0.3

app = FastAPI()

@app.get("/")
def read_root():
    return {"Hello": "World!"}