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

说明与用途

Durmain 是一个本地助手，记录通话音频，使用 faster‑whisper 进行转录，检测用户姓名，通话结束后使用 Ollama 的 Qwen2.5 7B 生成会议纪要，所有数据保存在本地。

问题

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.

结果

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%.

工作流

• 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

证据

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

来源

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

来源

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

来源

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.

来源

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.

来源