feat: use timestamps in file names

This allows us to run multiple recordings at once.
This commit is contained in:
2025-08-05 11:16:08 -07:00
parent 77bd353a21
commit 53f30437d9
3 changed files with 91 additions and 14 deletions
+3
View File
@@ -0,0 +1,3 @@
*.json
*.txt
*.wav
+4 -14
View File
@@ -1,20 +1,10 @@
# New Repository Template
# Meeting Minutes
This template contains all of our basic files for a new GitHub repository. There is also a handy workflow that will create an issue on a new repository made from this template, with a checklist for the steps we usually take in setting up a new repository.
If you're starting a Node.JS project with TypeScript, we have a [specific template](https://github.com/naomi-lgbt/nodejs-typescript-template) for that purpose.
## Readme
Delete all of the above text (including this line), and uncomment the below text to use our standard readme template.
<!-- # Project Name
Project Description
This is a local recording, transcription, and summarisation script that listens to your meeting and generates a summary. This is completely offline, to protect your data privacy.
## Live Version
This page is currently deployed. [View the live website.]
Gotta run it locally. Sorry!
## Feedback and Bugs
@@ -36,4 +26,4 @@ Copyright held by Naomi Carrigan.
## Contact
We may be contacted through our [Chat Server](http://chat.nhcarrigan.com) or via email at `contact@nhcarrigan.com`. -->
We may be contacted through our [Chat Server](http://chat.nhcarrigan.com) or via email at `contact@nhcarrigan.com`.
+84
View File
@@ -0,0 +1,84 @@
import subprocess
import json
import datetime
# === CONFIG ===
# Use current timestamp for file naming
TIMESTAMP = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
MEETING_FILE = f"meeting_audio_{TIMESTAMP}.wav"
WHISPER_MODEL = "small.en"
DURATION = 36000 # seconds (10 hour max)
OUTPUT_TRANSCRIPT = f"meeting_audio_{TIMESTAMP}.json"
OUTPUT_SUMMARY = f"summary_{TIMESTAMP}.txt"
def record_audio():
print("🎙 Recording meeting audio... (q to stop early)")
subprocess.run([
"ffmpeg",
"-f", "pulse", # Linux (change for Windows/macOS)
"-i", "default", # capture default input/output mix
"-t", str(DURATION),
"-ac", "2",
"-ar", "44100",
MEETING_FILE
], check=True)
def transcribe_audio():
print("🔠 Transcribing with WhisperX...")
subprocess.run([
# "pipenv run python3 -m whisperx",
"whisper",
MEETING_FILE,
"--device", "cpu", # Use CPU
"--language", "en",
# "--diarize", Put back when whisperX works.
"--model", WHISPER_MODEL,
"--output_format", "json",
"--output_dir", "."
], check=True)
def summarize_with_local_model():
print("🧾 Summarizing locally with Ollama...")
with open(OUTPUT_TRANSCRIPT, "r", encoding="utf-8") as f:
transcript = json.load(f)
text = "\n".join(
seg["text"]
for seg in transcript["segments"]
)
prompt = f"""Summarize this meeting transcript into clear bullet points with:
- Key decisions
- Action items
- Notable discussion points
Transcript:
{text}
"""
result = subprocess.run(
["ollama", "run", "llama3:8b"],
input=prompt.encode(),
capture_output=True,
check=True
)
summary = result.stdout.decode()
with open(OUTPUT_SUMMARY, "w", encoding="utf-8") as f:
f.write(summary)
print("✅ Summary written to", OUTPUT_SUMMARY)
def cleanup():
import os
if os.path.exists(MEETING_FILE):
os.remove(MEETING_FILE)
if os.path.exists(OUTPUT_TRANSCRIPT):
os.remove(OUTPUT_TRANSCRIPT)
if __name__ == "__main__":
record_audio()
transcribe_audio()
summarize_with_local_model()
cleanup()