• django@discuss.tchncs.de
    ·
    1 month ago

    There is nothing special going on. This whole project is just a bunch of python libraries coupled together to a cli tool. It uses the package SpeechRecognition to connect to the google speech recognition api: https://github.com/microsoft/markitdown/blob/main/src/markitdown/_markitdown.py#L691

    Pretty uninteresting and a bit disappointing. Pandoc is a lot more interesting.

    • utopiah@lemmy.ml
      ·
      1 month ago

      Thanks for the clarification. I checked the code you linked and noticed recognize_google and seems it's relying on https://github.com/Uberi/speech_recognition which then seems to rely on https://github.com/Uberi/speech_recognition/blob/master/speech_recognition/recognizers/google.py so basically are they using an API, sending all the audio data to Google servers?

      • django@discuss.tchncs.de
        ·
        1 month ago

        Yes, this is how I read it as well. The library would support to use a local model, but they decided to just send the audio data to Google.

        • utopiah@lemmy.ml
          ·
          1 month ago

          Might open up a GDPR related issue there. I don't think people using such a library assume they need connectivity nor that their data would be send to a 3rd party.