app.py

#import gradio as gr
#gr.Interface.load("models/pyannote/speaker-diarization").launch()

from fastapi import FastAPI, UploadFile
from fastapi.staticfiles import StaticFiles
from fastapi.responses import FileResponse
from audio.audioanalyser_anglais import AudioAnalyserAnglais
from audio.audioanalyser_diarization import AudioAnalyserDiarization
#from datasets import load_dataset, Audio # ça c'est pour entrainer mon modele


app = FastAPI()


@app.get("/healthcheck")
def healthcheck():
    
    #output = deepneurones(input)

    #pipeline("file.wav")
    return {"output":"OK"}
@app.post("/stt")
async def stt(file: str =  UploadFile(...)):
    #file_content = base64.b64decode(file)
    file_content = await file.read()
    results = AudioAnalyserAnglais.stt(file_content)
    #dataset = load_dataset("PolyAI/minds14", name="en-US", split="train")

    return {"output":results}
#app.mount("/", StaticFiles(directory="static", html=True), name="static")

@app.post("/diarization")
async def diarization(file: str =  UploadFile(...)):
    #file_content = base64.b64decode(file)
    file_content = await file.read()
    results = AudioAnalyserDiarization.diarization(file_content)
    #dataset = load_dataset("PolyAI/minds14", name="en-US", split="train")

    return {"output":results}
#app.mount("/", StaticFiles(directory="static", html=True), name="static")


@app.get("/")
def index() -> FileResponse:
    return FileResponse(path="/home/user/app/index.html", media_type="text/html")