File size: 3,523 Bytes
819e875 e04f2c1 819e875 34365ef 819e875 c246438 819e875 08eb9a4 819e875 34365ef 819e875 e04f2c1 c50abfa 819e875 e04f2c1 68fb125 e04f2c1 68fb125 e04f2c1 819e875 e04f2c1 819e875 da9cb3e 34365ef 819e875 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
import streamlit as st
from pathlib import Path
import tempfile, subprocess, threading, queue
import textwrap
import streamlit.components.v1 as components
st.set_page_config(page_title="Lec2Note2 – Lecture-to-Notes", layout="wide")
st.title("📝 Lec2Note – Automatic Lecture Notes Generator")
# Inject MathJax once for LaTeX rendering
MATHJAX = "<script src='https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js'></script>"
components.html(MATHJAX, height=0)
st.markdown(
textwrap.dedent(
"""
Upload a lecture **video** and receive a fully-formatted **Markdown** study note – complete with key images and structured sections.
The processing pipeline performs ASR transcription, vision & semantic segmentation, then invokes an LLM to produce rich notes.
"""
)
)
video_file = st.file_uploader("🎬 Upload MP4/MKV/AVI", type=["mp4", "mkv", "avi"])
run_btn = st.button("🚀 Generate Notes", disabled=video_file is None)
if run_btn and video_file:
# Save upload to a temporary file
tmp_dir = tempfile.TemporaryDirectory()
vid_path = Path(tmp_dir.name) / video_file.name
with vid_path.open("wb") as f:
f.write(video_file.read())
output_md = vid_path.with_suffix(".md")
st.info("Processing started. This may take several minutes depending on video length …")
# container for live log streaming
log_container = st.container()
log_placeholder = log_container.code("", language="bash", height=300)
# Run pipeline via subprocess to avoid blocking UI; capture logs
with st.spinner("Running Lec2Note2 pipeline …"):
# launch pipeline in subprocess with unbuffered output
cmd = [
"python",
"-u", # unbuffer stdout
"-m",
"lec2note.scripts.run_pipeline",
"--video",
str(vid_path),
"--output",
str(output_md),
]
proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
log_queue: "queue.Queue[str]" = queue.Queue()
def _enqueue_output(pipe, q):
for line in iter(pipe.readline, ""):
q.put(line)
pipe.close()
threading.Thread(target=_enqueue_output, args=(proc.stdout, log_queue), daemon=True).start()
logs = ""
line_count = 0
while True:
try:
line = log_queue.get(timeout=0.1)
except queue.Empty:
if proc.poll() is not None:
# process finished and queue empty
break
continue
logs += line
line_count += 1
if line_count % 5 == 0: # update UI every 5 lines to reduce overhead
log_placeholder.code(logs, language="bash", height=300)
# final flush
log_placeholder.code(logs, language="bash", height=300)
result_code = proc.wait()
if result_code != 0:
st.error("❌ Pipeline failed. See logs below.")
with st.expander("Show logs"):
st.code(logs)
else:
st.success("✅ Notes generated!")
md_content = output_md.read_text()
with st.container(border=True):
st.markdown(md_content, unsafe_allow_html=True)
st.download_button(
label="💾 Download notes.md",
data=md_content,
file_name="lecture_notes.md",
mime="text/markdown",
)
tmp_dir.cleanup()
|