File size: 1,388 Bytes
d7d0d8e 252d749 385a3d3 252d749 d7d0d8e 252d749 d7d0d8e 385a3d3 78f1df3 d7d0d8e 385a3d3 af60251 7306982 385a3d3 7306982 dd2695b af5c58a 7306982 385a3d3 dd2695b b745b4d d7d0d8e dd2695b d7d0d8e |
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 |
from celery import Celery, chain
import os
import time
from App import celery_config
import yt_dlp
import tempfile
from App.Transcription.Utils.audio_transcription import transcribe_file
from App.Embedding.utils.Initialize import encode, generateChunks
celery = Celery()
celery.config_from_object(celery_config)
@celery.task(name="embbeding", bind=True)
def generate_store(self, data, task_id):
chunks = generateChunks(data, task_id)
encode(chunks)
print("hellooo")
@celery.task(name="transcription", bind=True)
def transcription_task(self, file_path, model_size="tiny"):
# data = transcribe_file(state=self, file_path=file_path, model_size=model_size)
chunks = generateChunks(data["content"], task_id)
encode(chunks)
return data
@celery.task(name="download", bind=True)
def downloadfile(self, url, ydl_opts, model_size="base"):
# updated
self.update_state(state="Downloading File..", meta={})
####
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
ydl.download([url])
# updated
self.update_state(state="Downloading complete", meta={})
audio_file = ydl_opts["outtmpl"]
print(model_size,'worker after')
# print(audio_file["default"])
data = transcribe_file(
state=self, file_path=audio_file["default"], model_size=model_size
)
generate_store.delay(data["content"], self.request.id)
return data
|