feat: VoiceScript STT+OCR 초기 버전

app/tasks.py

@@ -0,0 +1,97 @@
+import os
+from celery import Celery
+
+# ocr_task를 직접 import해서 worker에 등록
+from ocr_tasks import ocr_task  # noqa: F401
+
+REDIS_URL      = os.getenv("REDIS_URL", "redis://redis:6379/0")
+MODEL_SIZE     = os.getenv("WHISPER_MODEL", "medium")
+DEVICE         = os.getenv("WHISPER_DEVICE", "cpu")
+COMPUTE_TYPE   = os.getenv("WHISPER_COMPUTE_TYPE", "int8")
+LANGUAGE       = os.getenv("WHISPER_LANGUAGE", "ko") or None
+BEAM_SIZE      = int(os.getenv("WHISPER_BEAM_SIZE", "5"))
+INITIAL_PROMPT = os.getenv("WHISPER_INITIAL_PROMPT", "") or None
+OUTPUT_DIR     = os.getenv("OUTPUT_DIR", "/data/outputs")
+
+celery_app = Celery("whisper_tasks", broker=REDIS_URL, backend=REDIS_URL)
+celery_app.conf.update(
+    task_serializer="json",
+    result_serializer="json",
+    accept_content=["json"],
+    task_track_started=True,
+    result_expires=3600,
+)
+
+_model = None
+
+def get_model():
+    global _model
+    if _model is None:
+        from faster_whisper import WhisperModel
+        print(f"[Whisper] 로딩: {MODEL_SIZE} / {DEVICE} / {COMPUTE_TYPE}")
+        _model = WhisperModel(MODEL_SIZE, device=DEVICE, compute_type=COMPUTE_TYPE)
+        print("[Whisper] 로드 완료")
+    return _model
+
+
+@celery_app.task(bind=True, name="tasks.transcribe_task", queue="stt")
+def transcribe_task(self, file_id: str, audio_path: str):
+    self.update_state(state="PROGRESS", meta={"progress": 5, "message": "모델 준비 중..."})
+    try:
+        model = get_model()
+        self.update_state(state="PROGRESS", meta={"progress": 15, "message": "오디오 분석 중..."})
+
+        segments_gen, info = model.transcribe(
+            audio_path,
+            language=LANGUAGE,
+            beam_size=BEAM_SIZE,
+            initial_prompt=INITIAL_PROMPT,
+            vad_filter=True,
+            vad_parameters=dict(min_silence_duration_ms=500),
+            word_timestamps=False,
+        )
+
+        self.update_state(state="PROGRESS", meta={"progress": 30, "message": "텍스트 변환 중..."})
+
+        segments, full_text_parts = [], []
+        duration = info.duration
+
+        for seg in segments_gen:
+            segments.append({"start": round(seg.start, 2),
+                             "end":   round(seg.end, 2),
+                             "text":  seg.text.strip()})
+            full_text_parts.append(seg.text.strip())
+            if duration > 0:
+                pct = 30 + int((seg.end / duration) * 60)
+                self.update_state(
+                    state="PROGRESS",
+                    meta={"progress": min(pct, 90),
+                          "message": f"변환 중... {seg.end:.0f}s / {duration:.0f}s"},
+                )
+
+        full_text = "\n".join(full_text_parts)
+
+        self.update_state(state="PROGRESS", meta={"progress": 95, "message": "파일 저장 중..."})
+        os.makedirs(OUTPUT_DIR, exist_ok=True)
+        output_filename = f"{file_id}.txt"
+        with open(os.path.join(OUTPUT_DIR, output_filename), "w", encoding="utf-8") as f:
+            f.write(f"# 변환 결과\n# 언어: {info.language}  |  재생 시간: {duration:.1f}초\n\n")
+            f.write("## 전체 텍스트\n\n" + full_text + "\n\n")
+            f.write("## 타임스탬프별 세그먼트\n\n")
+            for seg in segments:
+                f.write(f"[{_fmt(seg['start'])} → {_fmt(seg['end'])}]  {seg['text']}\n")
+
+        try: os.remove(audio_path)
+        except: pass
+
+        return {"text": full_text, "segments": segments,
+                "language": info.language, "duration": round(duration, 1),
+                "output_file": output_filename}
+
+    except Exception as e:
+        raise Exception(f"변환 실패: {str(e)}")
+
+
+def _fmt(s):
+    m, sec = divmod(int(s), 60)
+    return f"{m:02d}:{sec:02d}"