import os
import re
import tempfile
import time
import traceback
import gradio as gr
import httpx
import yt_dlp
try:
import spaces
except ImportError:
class spaces:
@staticmethod
def GPU(duration=60):
def decorator(fn):
return fn
return decorator
PROXY_BASE = os.environ.get("PROXY_BASE", "").rstrip("/")
PROXY_TOKEN = os.environ.get("PROXY_TOKEN", "")
from transcribe import transcribe_audio, unload_model as unload_whisper
from lecture_processor import summarize_lecture, generate_quiz
# LANGUAGES = {
# "Auto-detect": None,
# "English": "en",
# "Korean": "ko",
# "Japanese": "ja",
# "Chinese": "zh",
# "Spanish": "es",
# "French": "fr",
# "German": "de",
# "Italian": "it",
# "Portuguese": "pt",
# "Russian": "ru",
# "Arabic": "ar",
# "Hindi": "hi",
# }
def get_youtube_video_id(url: str) -> str | None:
"""Extract video ID from various YouTube URL formats."""
patterns = [
r"(?:youtube\.com/watch\?v=|youtu\.be/|youtube\.com/embed/)([a-zA-Z0-9_-]{11})",
]
for pattern in patterns:
match = re.search(pattern, url)
if match:
return match.group(1)
return None
def make_embed_html(video_id: str) -> str:
return f''
def download_youtube_audio(url: str) -> str:
"""Download audio from YouTube URL, returns path to wav file."""
tmp_dir = tempfile.mkdtemp()
output_path = f"{tmp_dir}/audio.wav"
ydl_opts = {
"format": "bestaudio/best",
"postprocessors": [{
"key": "FFmpegExtractAudio",
"preferredcodec": "wav",
}],
"outtmpl": f"{tmp_dir}/audio",
"quiet": True,
"no_warnings": True,
}
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
ydl.download([url])
return output_path
LANGUAGES = {
"English": "en",
}
def make_status_html(step: int = 0, timing: str = "", error: str = "") -> str:
"""Step progress indicator. Steps: 0=idle, 1=download, 2=transcribe, 3=summarize, 4=quiz, 5=done."""
if error:
return f'{error}
'
if step == 0:
return ""
labels = ["Download", "Transcribe", "Summarize", "Quiz"]
items = []
for i, label in enumerate(labels):
s = i + 1
if s < step or step == 5:
cls, icon = "done", "✓"
elif s == step:
cls, icon = "active", "↻"
else:
cls, icon = "pending", str(s)
items.append(
f'{icon}{label}
'
)
connector = ''
steps_html = connector.join(items)
timing_html = f'{timing}
' if timing else ""
return f'{steps_html}
{timing_html}
