There is one guy that does the same for batteries, chargers, power supplies and more: https://lygte-info.dk/

Guess what. Lamptest guy from my comment above tests batteries as well. Here are his websites for this project (same data but different design): https://battest.ru/ https://batterytest.ru/

Thank you. Had been looking for something like this! Batteries are one of these items where you really don’t know what you’re getting.

Works great! However, i had Python 3.11 set up as default python3 in path, and since there is no wheel for torch for 3.11 yet, the script failed. With 3.10 it worked flawlessly.

Small improvement: the node script could check if the model files are already present at the download location and not download them again in this case.

Happened to me as well. Apparently, you can just run:

   python3.10 convert-pth-to-ggml.py models/7B 1
   ./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin 2

And then play with:

    ./main -m ./models/7B/ggml-model-q4_0.bin -t 8 -n 128 -p "..."

I agree, ncdu is a great and easy to use command line tool.

On Mac OS, run for example:

   ncdu -x --exclude /Volumes --exclude /System/Volumes /

This scans the root filesystem but excludes the Volume mounts specifically (the -x option to limit the scan to the current filesystem doesn't work properly on mac os). Navigate through the folders, sorted by size, from there. Press d to delete a folder.

Oh wow thank you

I tried running it in realtime with live audio input (kind of).

If you want to give it a shot, you can find the python script in this repo: https://github.com/tobiashuttinger/openai-whisper-realtime

A bit more context on how it works: The systems default audio input is captured with python, split into small chunks and is then fed to OpenAI's original transcription function. It tries (currently rather poorly) to detect word breaks and doesn't split the audio buffer in those cases. With how the model is designed, it doesn't make the most sense to do this, but i found it would be worth trying. It works acceptably well.

Haven’t tried it yet but love the concept!

Have you thought of using VAD (voice activity detection) for breaks? Back in my day (a long time ago) the webrtc VAD stuff was considered decent:

https://github.com/wiseman/py-webrtcvad

Model isn’t optimized for this use but I like where you’re headed!

Interesting. I'll take a look at this, thanks!

Perhaps this could be adapted?

https://github.com/mozilla/DeepSpeech-examples/blob/master/m...