klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-06 13:22:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Move transcription using OpenAI API into independent package

Browse Source
This commit is contained in:
Debanjum Singh Solanky
2023-11-26 02:32:15 -08:00
parent 897170ab15
commit 499adf86a0
2 changed files with 19 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/khoj/processor/conversation/openai/whisper.py Normal file
View File

@@ -0,0 +1,15 @@
# Standard Packages
from io import BufferedReader
# External Packages
from asgiref.sync import sync_to_async
import openai
async def transcribe_audio(audio_file: BufferedReader, model, api_key) -> str | None:
"""
Transcribe audio file using Whisper model via OpenAI's API
"""
# Send the audio data to the Whisper API
response = await sync_to_async(openai.Audio.translate)(model=model, file=audio_file, api_key=api_key)
return response["text"]

11
src/khoj/routers/api.py
View File

@@ -10,10 +10,9 @@ import uuid
# External Packages
from asgiref.sync import sync_to_async
from fastapi import APIRouter, Depends, File, Header, HTTPException, Request, UploadFile
from fastapi import APIRouter, Depends, File, HTTPException, Request, UploadFile
from fastapi.requests import Request
from fastapi.responses import Response, StreamingResponse
import openai
from starlette.authentication import requires
# Internal Packages
@@ -33,6 +32,7 @@ from khoj.database.models import (
)
from khoj.processor.conversation.gpt4all.chat_model import extract_questions_offline
from khoj.processor.conversation.openai.gpt import extract_questions
from khoj.processor.conversation.openai.whisper import transcribe_audio
from khoj.processor.conversation.prompts import help_message, no_entries_found
from khoj.processor.tools.online_search import search_with_google
from khoj.routers.helpers import (
@@ -589,7 +589,7 @@ async def chat_options(
@api.post("/speak")
@requires(["authenticated"])
async def transcribe_audio(request: Request, common: CommonQueryParams, file: UploadFile = File(...)):
async def transcribe(request: Request, common: CommonQueryParams, file: UploadFile = File(...)):
user: KhojUser = request.user.object
audio_filename = f"{user.uuid}-{str(uuid.uuid4())}.webm"
user_message: str = None
@@ -611,10 +611,7 @@ async def transcribe_audio(request: Request, common: CommonQueryParams, file: Up
elif speech_to_text_config.model_type == ChatModelOptions.ModelType.OPENAI:
api_key = openai_chat_config.api_key
speech2text_model = speech_to_text_config.model_name
response = await sync_to_async(openai.Audio.translate)(
model=speech2text_model, file=audio_file, api_key=api_key
)
user_message = response["text"]
user_message = await transcribe_audio(model=speech2text_model, audio_file=audio_file, api_key=api_key)
finally:
# Close and Delete the temporary audio file
audio_file.close()