aaronchantrill

I'm not ready to close this. I have a lot of stuff that I'm working on at the moment, but this should be easy for someone to implement through a...

I think the two main things I want to do are to move the NPE stuff out of application.py into its own file and move the audiolog stuff out of...

I am working on this, and the reliability of VOSK is pretty amazing. It is also pretty lightweight and easy to install. I am currently trying to adapt the Language...

> add_subdirectory given source "stream" which is not an existing directory. > add_subdirectory given source "builder" which is not an existing directory. > add_subdirectory given source "filter" which is not...

The problem (for me) appears to be that the DeepSpeech folk don't link to or include the entirety of this project in the DeepSpeech/native_client/kenlm folder, they only include enough of...

I'm planning to do slot types now. If you want a numeric value, you would create a template like "Count from {from:number} to {to:number}" When we pass the templates to...

Python 2.7 is no longer available with Debian Bookworm. I was able to edit the check_dependencies.sh script in tools to get past that check, and then created the python directory...

I'm happy to hear that you are interested in Naomi. Naomi is primarily aimed at being easy to develop on. The idea is that users can write plugins for different...

How are you using Whisper in your own projects? We usually need to be able to customize the dictionary somewhat, usually because of people, place, album, song, etc. names that...

After upgrading to Debian Bullseye and Pipewire, the above stopped working again. I decided to start it as a systemd service this time, so put the following into ~/.config/naomi/Naomi_start.sh: ```...