.

Dockerfile

@@ -0,0 +1,18 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+
+

app.py

@@ -0,0 +1,65 @@
+import os
+import shutil
+from fastapi import FastAPI, File, UploadFile, Form
+from fastapi.responses import FileResponse, JSONResponse
+import whisper
+
+app = FastAPI()
+
+# Whisper 모델 로드 (필요에 따라 모델 크기를 선택하세요)
+model = whisper.load_model("tiny")  # "tiny", "base", "small", "medium", "large-v2" 등
+
+@app.post("/transcribe/")
+async def transcribe_video(
+    file: UploadFile = File(...),
+    language: str = Form("en")  # 언어 선택 가능 (기본값: 영어)
+):
+    """
+    Upload a video/audio file and get the generated SRT file as a response.
+    """
+    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")
+        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
+
+                # 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'
+        )
+    
+    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)

requirements.txt

@@ -0,0 +1,5 @@
+torch  # PyTorch는 Whisper 모델을 실행하기 위해 필요합니다.
+whisper  # Whisper 라이브러리를 설치합니다.
+
+fastapi  # FastAPI 프레임워크
+uvicorn  # FastAPI 서버 실행을 위한 Uvicorn ASGI 서버