I don't listen to meetings anymore. My sloth does.

Описание и применение

Durmain — локальный помощник, который записывает аудио звонка, распознаёт речь с помощью faster‑whisper, обнаруживает упоминание имени пользователя и после окончания звонка генерирует протокол с помощью Ollama и модели Qwen2.5 7B, при этом данные не покидают ноутбук.

Задача

Taking notes in a meeting is expensive and often done poorly because the speaker is simultaneously being transcribed and listened to, and most transcription tools send audio to third‑party servers.

Результат

Durmain achieved 8/10 name detections with 0 false alarms in live calls, 16/20 in scripted recordings, produced minutes in ~36 s for a 20‑minute lecture, and used 583 MB RAM with CPU spikes of 40‑50%.

Рабочий процесс

• Record system audio via pyaudiowpatch in 5‑second blocks
• Transcribe blocks with faster‑whisper (model small, int8) and VAD
• Detect user’s name in transcript using rapidfuzz
• When name detected, display sloth overlay and start live note taking
• After call ends, send transcript to Ollama (qwen2.5:7b) to produce minutes
• Save minutes locally

Доказательства

Durmain listens to your computer's audio, transcribes it locally, and stays asleep until your name comes up.

Источник

The pipeline is simple: system audio ─► 5 s blocks ─► faster-whisper + VAD ─► transcript │ │ ▼ ▼ when the call ends name detector ─► sloth Ollama (qwen2.5:7b) ─► minutes

Источник

Everything runs on your machine. No audio or text ever leaves it.

Источник

The first time I paused a video, the transcript said "Legendas pela comunidade Amara.org"… Whisper learned from subtitled videos, so silence turns into subtitle credits.

Источник

I built this with an AI coding assistant acting as a mentor… wrote some of the glue code (the Ollama call, the overlay) so I could make the deadline.

Источник