generated from nhcarrigan/template
feat: use timestamps in file names
This allows us to run multiple recordings at once.
This commit is contained in:
@@ -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()
|
||||
Reference in New Issue
Block a user