interface

app.py

@@ -0,0 +1,108 @@
+import gradio as gr
+import whisper
+import subprocess
+import os
+import uuid
+import torch
+import re
+import nltk
+from nltk.tokenize import sent_tokenize
+from transformers import pipeline, AutoTokenizer
+
+# NLTK 리소스 다운로드
+nltk.download('punkt')
+
+# 🔊 Whisper 자막 생성 모델
+asr_model = whisper.load_model("medium")
+
+# 🧠 요약 모델 (mT5 기반 다국어 요약 지원)
+model_name = "csebuetnlp/mT5_multilingual_XLSum"
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
+summarizer = pipeline("summarization", model=model_name, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+
+# yt-dlp 및 ffmpeg 경로 설정
+yt_dlp_path = "C:/Windows/System32/yt-dlp.exe"
+ffmpeg_path = "C:/ProgramData/chocolatey/bin"
+
+# 🎵 오디오 다운로드 함수
+def download_audio_with_ytdlp(youtube_url):
+    audio_filename = f"yt_audio_{uuid.uuid4().hex[:8]}.mp3"
+    command = [
+        yt_dlp_path,
+        "-f", "bestaudio",
+        "--extract-audio",
+        "--audio-format", "mp3",
+        "--ffmpeg-location", ffmpeg_path,
+        "-o", audio_filename,
+        youtube_url
+    ]
+    try:
+        subprocess.run(command, capture_output=True, text=True, check=True)
+        if not os.path.exists(audio_filename):
+            raise RuntimeError(f"오디오 파일 생성 실패: {audio_filename}")
+        return audio_filename
+    except subprocess.CalledProcessError as e:
+        raise RuntimeError(f"yt-dlp 실행 오류:\n{e.stderr}")
+
+# 📄 자막 정제
+def clean_transcript(raw_text):
+    text = re.sub(r'\s+', ' ', raw_text).strip()
+    return sent_tokenize(text)
+
+# 🧠 자막을 분할하여 요약
+def summarize_long_text(text, chunk_char_limit=1000):
+    sentences = clean_transcript(text)
+    chunks, current_chunk = [], ""
+
+    for sentence in sentences:
+        if len(current_chunk) + len(sentence) < chunk_char_limit:
+            current_chunk += sentence + " "
+        else:
+            chunks.append(current_chunk.strip())
+            current_chunk = sentence + " "
+    if current_chunk:
+        chunks.append(current_chunk.strip())
+
+    summaries = []
+    for chunk in chunks:
+        try:
+            result = summarizer(chunk, max_length=128, min_length=30, do_sample=False)
+            summaries.append(result[0]['summary_text'])
+        except:
+            summaries.append("⚠️ 요약 실패")
+
+    return "\n\n".join(summaries)
+
+# 🔁 전체 처리 파이프라인
+def process_youtube(youtube_url):
+    try:
+        audio_file = download_audio_with_ytdlp(youtube_url)
+        result = asr_model.transcribe(audio_file)
+        transcript = result.get("text", "")
+
+        if os.path.exists(audio_file):
+            os.remove(audio_file)
+
+        if len(transcript.strip()) < 100:
+            summary = "⚠️ 자막 내용이 너무 짧아 요약할 수 없습니다."
+        else:
+            summary = summarize_long_text(transcript)
+
+        return transcript, summary
+    except Exception as e:
+        return f"[에러] {str(e)}", ""
+
+# 🌐 Gradio UI 구성
+demo = gr.Interface(
+    fn=process_youtube,
+    inputs=gr.Textbox(label="유튜브 영상 URL"),
+    outputs=[
+        gr.Textbox(label="🎙 자막 (Whisper 결과)", lines=10),
+        gr.Textbox(label="🧠 요약 (요약 결과)", lines=5)
+    ],
+    title="🎬 유튜브 자막 & 요약 서비스 (한/영 혼합 최적화)",
+    description="yt-dlp로 오디오 다운로드 → Whisper 자막 생성 → mT5 요약 모델로 요약 처리"
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+openai-whisper
+torch
+transformers
+nltk
+yt-dlp