.

.env

@@ -0,0 +1,2 @@
+SMTP_USER=kyowoon.lee1924@gmail.com
+SMTP_PASSWORD=rhwy amyv hdwq pspa

app.py

@@ -1,65 +1,126 @@
 import os
-import shutil
-from fastapi import FastAPI, File, UploadFile, Form
-from fastapi.responses import FileResponse, JSONResponse
+import re
+import uuid
+import gdown
 import whisper
+import smtplib
+from email.mime.text import MIMEText
+from email.mime.multipart import MIMEMultipart
+from concurrent.futures import ThreadPoolExecutor
+from fastapi import FastAPI, HTTPException, BackgroundTasks
+from fastapi.responses import JSONResponse
+from dotenv import load_dotenv
 
-app = FastAPI()
+# 구글 드라이브 링크, 어떤 언어, 받을 이메일 주소
 
-# Whisper 모델 로드 (필요에 따라 모델 크기를 선택하세요)
-model = whisper.load_model("tiny")  # "tiny", "base", "small", "medium", "large-v2" 등
+# .env 파일에서 중요한 환경 변수 로드
+load_dotenv()
 
-@app.post("/transcribe/")
-def transcribe_video(
-    file: UploadFile = File(...),
-    language: str = Form("en")  # 언어 선택 가능 (기본값: 영어)
-):
+app = FastAPI(
+    version="0.0.1",
+    servers=[
+        {
+            "url": "https://leekwoon-whisper-api.hf.space",
+            "description": "video/audio transcription API",
+        }
+    ],
+)
+
+# Whisper 모델 로드
+model = whisper.load_model("tiny")
+
+executor = ThreadPoolExecutor(max_workers=3)  # 최대 3개의 스레드로 비동기 작업 처리
+
+def extract_file_id(drive_url: str) -> str:
     """
-    Upload a video/audio file and get the generated SRT file as a response.
+    Google Drive URL에서 파일 ID를 추출합니다.
     """
+    match = re.search(r'/d/([a-zA-Z0-9_-]+)', drive_url)
+    if match:
+        return match.group(1)
+    match = re.search(r'file/d/([a-zA-Z0-9_-]+)', drive_url)
+    if match:
+        return match.group(1)
+    match = re.search(r'([a-zA-Z0-9_-]{33,})', drive_url)
+    if match:
+        return match.group(1)
+    raise ValueError("Invalid Google Drive URL")
+
+def send_email(to_email: str, srt_file_path: str, transcription_time: float):
+    smtp_server = "smtp.gmail.com"
+    smtp_port = 587
+    smtp_user = os.getenv("SMTP_USER")
+    smtp_password = os.getenv("SMTP_PASSWORD")
+
+    subject = "[kyobody - 자막생성] 작업이 완료되었습니다."
+    body = f"[kyobody - 자막생성] 작업이 완료되었습니다. 총 소요 시간: {transcription_time:.2f} 초. SRT 파일을 첨부합니다."
+
+    msg = MIMEMultipart()
+    msg["From"] = smtp_user
+    msg["To"] = to_email
+    msg["Subject"] = subject
+
+    msg.attach(MIMEText(body, "plain"))
+
+    with open(srt_file_path, "r") as file:
+        attachment = MIMEText(file.read())
+        attachment.add_header("Content-Disposition", "attachment", filename=os.path.basename(srt_file_path))
+        msg.attach(attachment)
+
+    with smtplib.SMTP(smtp_server, smtp_port) as server:
+        server.starttls()
+        server.login(smtp_user, smtp_password)
+        server.sendmail(smtp_user, to_email, msg.as_string())
+
+def transcribe_and_send_email(temp_input_file: str, srt_file_path: str, email: str):
     try:
-        # Create a temporary directory
-        temp_dir = "temp"
-        os.makedirs(temp_dir, exist_ok=True)
-
-        # Save the uploaded file temporarily
-        input_file_path = os.path.join(temp_dir, file.filename)
-        with open(input_file_path, "wb") as buffer:
-            shutil.copyfileobj(file.file, buffer)
-        
-        # Transcribe the file using Whisper
-        result = model.transcribe(input_file_path, language=language)
-
-        # SRT 파일 생성
-        srt_file_path = os.path.join(temp_dir, "output.srt")
+        # Transcribe the video/audio file
+        import time
+        start_time = time.time()
+        result = model.transcribe(temp_input_file)
+        transcription_time = time.time() - start_time
+
+        # Save the transcription to an SRT file
         with open(srt_file_path, "w") as srt_file:
             for i, segment in enumerate(result["segments"]):
                 start = segment['start']
                 end = segment['end']
-                text = segment['text'][1:]  # Remove leading space
+                text = segment['text'][1:]
 
-                # 타임스탬프 형식 변환 (SRT 형식에 맞게)
                 start_time = f"{int(start // 3600):02}:{int((start % 3600) // 60):02}:{int(start % 60):02},{int((start * 1000) % 1000):03}"
                 end_time = f"{int(end // 3600):02}:{int((end % 3600) // 60):02}:{int(end % 60):02},{int((end * 1000) % 1000):03}"
 
-                # SRT 파일에 기록
                 srt_file.write(f"{i + 1}\n")
                 srt_file.write(f"{start_time} --> {end_time}\n")
                 srt_file.write(f"{text}\n\n")
-        
-        # Return the SRT file as a response
-        return FileResponse(
-            path=srt_file_path,
-            filename="output.srt",
-            media_type='application/x-subrip'
-        )
-    
+
+        # Send the result via email
+        send_email(email, srt_file_path, transcription_time)
+
+        # Clean up the temporary files
+        os.remove(temp_input_file)
+        os.remove(srt_file_path)
+
+    except Exception as e:
+        print(f"Error in transcription or email sending: {e}")
+
+@app.post("/transcribe/")
+def transcribe_video(url: str, email: str, background_tasks: BackgroundTasks):
+    try:
+        # Extract file ID and download the file
+        file_id = extract_file_id(url)
+        download_url = f"https://drive.google.com/uc?id={file_id}"
+        temp_input_file = f'/tmp/{uuid.uuid4()}.mp4'
+        gdown.download(download_url, temp_input_file, quiet=False)
+
+        # Define SRT file path
+        srt_file_path = f'/tmp/{uuid.uuid4()}.srt'
+
+        # Schedule the transcription and email sending in the background
+        background_tasks.add_task(executor.submit, transcribe_and_send_email, temp_input_file, srt_file_path, email)
+
+        # Respond to the client immediately
+        return JSONResponse(status_code=202, content={"message": "Transcription started, you will receive an email when it's done."})
+
     except Exception as e:
-        return JSONResponse(status_code=500, content={"message": str(e)})
-    
-    finally:
-        # Clean up temporary files
-        if os.path.exists(input_file_path):
-            os.remove(input_file_path)
-        if os.path.exists(srt_file_path):
-            os.remove(srt_file_path)
+        raise HTTPException(status_code=500, detail=str(e))

requirements.txt

@@ -3,4 +3,5 @@ openai-whisper  # Whisper 라이브러리를 설치합니다.
 
 fastapi  # FastAPI 프레임워크
 uvicorn  # FastAPI 서버 실행을 위한 Uvicorn ASGI 서버
-python-multipart
+python-dotenv
+gdown