5 Good Open Source Speech Recognition/Speech-to-Text Systems

5 Good Open Source Speech Recognition/Speech-to-Text Systems:

  1. Project DeepSpeech from Mozilla:pip3 install deepspeech deepspeech –model models/output_graph.pbmm –alphabet models/alphabet.txt –lm models/lm.binary –trie models/trie –audio my_audio_file.wavYou can also install it using npm:
    npm install deepspeech

    For more information, refer to the project’s homepage.

  2. Kaldi
  3. Julius should be already packaged for many distro
  4. Wav2letter++
  5. DeepSpeech2 from the Chinese giant Baidu

classic improved – Gnome-look.org

A MacOs 9 or “classic” theme for Metacity. I may borrow some ideas for a WordPress theme….


This is an improved version of the Metacity theme classic by servo.
It has now a more authentic resemblance of the original MacOS 8/9 Platinum Theme, including a 1px black shadow and working pressed button states for window buttons.

To use the right Button arrangement use this command:

gconftool-2 –type=string
–set /apps/metacity/general/button_layout close:maximize,minimize

I use Sans 9,5 px at 94 dpi for my Window Title Font. I also use the Xfce Saltlake theme.

To get the “classic”, old-style look’n’feel of MacOs the original fonts should be used: Charcoal, Chicago,Geneva and Monaco typefaces but I suspect that Apple would have something to object. Sadly there are few “liberi” typefaces available, as identifonts tells us. I suspect that some simple, blocky sans font would suffice, perhaps Code New Roman:

This font improved and based on Mac OS Western New Roman,MONACO