Advanced Search
Search Results
42 total results found
From Voice to Text
Discord (Legcord) ↓ PipeWire graph ↓ discord_sink (virtual null sink) ↓ discord_sink.monitor (loopback source) ↓ whisper_mic (remap-source, mono, 16kHz) ↓ ffmpeg ↓ audio.wav (growing file) ↓ whisper-stream On the device us...
Things to Look Into
https://picovoice.ai/blog/whisper-cpp-speaker-diarization/ OpenAI Whisper delivers highly accurate speech-to-text transcription, but it does not track speaker changes. Applications that rely on Whisper cannot determine who is speaking in a conversation. To...
Voice Activity Detection
In the whisper.cpp built used in this example, Voice Activity Detection does not exist. mela@Cox:~/meetings/lib $ error: unknown argument: --vad Voice Activity Detection, if present, enables whisper.cpp to only transcribe when somebody is actually talking...
Postponed
I most likely won't work creating summaries in this iteration of the project. Look out for the future Mini-PC version.
Pre-Session Checklist
Boot your Raspberry Pi Sign into your Raspberry Pi's GUI (Optional) Check if Syncthing is running Start Legcord & log into your dedicated second account Check if all participants consented to have their voices recorded - the goal is informed consent Enter the...
Storage & Preventing Data Loss
SD Cards Are Not (Really) a Storage Medium You need to set up Syncthing not only on the device you are using to create the transcripts, but also on your main computer — or any computer in your network, you like to store the finished transcripts on. The Raspbe...
Beyond a Raspberry Pi 500 …
If you want to try to get better results than I was able to produce, consider using a Raspberry Pi 5 with the maximum RAM configuration (16GB), an add-on board for SSD storage and a case with integrated fan. As the market for memory has been significantly imp...
(Optional) Activating VNC
Consider this if you want to run TranscriptOMatic without a display hooked up to the device. VNC allows you to access the Raspberry Pi desktop remotely from another computer. Log into your Raspberry Pi — either via ssh or via GUI, if you have a monitor (and k...
Post-Session Checklist
Stop meeting-follow (Ctrl+C) Start meeting-stop Enter the session's title Leave the voice channel and close Legcord Delete the recording (Optional) Check if Syncthing has synced the files to your main computer Check that the recording is deleted on all co...
Preventing Interference
In Legcord, open the Discord Voice & Video settings: Setting all Sounds to off Setting the Soundboard Volume to off Discord's notification sounds and soundboard audio would otherwise be picked up by the virtual microphone and fed into the transcription,...
TranscriptOMatic - The Raspberry Pi Version
How to set up 'almost good-enough almost real-time' TTRPG session transcription on a Raspberry Pi 500, using only Open-Source tools and a local language model.
The Scripts
TranscriptOMatic consists of the following scripts. In addition: Don't forget to create the needed files and folders and set the right permissions.
Appendix
Additional information and thoughts for the future.
Difficulties
Be aware of this technical and ethical pitfalls.
Creating Summaries
Postponed
Things (Also) to Consider …
How to keep your transcripts safe and how to get (maybe) better results.
Running TranscriptOMatic
Now that everything is prepared and checked, what now?
How To Set-Up
Before you can run the scripts, there is to lay some groundwork first.