search

ElishaAz / Sayboard

An open-source on-device voice IME (keyboard) for Android using the Vosk library.
GNU General Public License v3.0
304 stars 19 forks source link

sherpa-ncnn as backend? #36

Open rhjdvsgsgks opened 8 months ago

rhjdvsgsgks commented 8 months ago

hi. i found that there is another speech recognition project which may provide better result than vosk. do you have interest of integrate it with sayboard? https://github.com/k2-fsa/sherpa-ncnn

ElishaAz commented 8 months ago

Sounds interesting. I'll take a look

MXC48 commented 8 months ago

it might be a good idea to add this language model too https://github.com/coqui-ai/STT-models

csukuangfj commented 7 months ago

Sounds interesting. I'll take a look

Any updates? I would like to provide any help if you have any issues.

csukuangfj commented 7 months ago

By the way, http://github.com/k2-fsa/sherpa-onnx is also a good candidate. It supports both streaming and non-streaming speech-to-text as well as text-to-speech.

ElishaAz commented 7 months ago

Any updates? I would like to provide any help if you have any issues.

Sorry, I'm busy right now.

The main problem with these projects is that they don't provide binaries on Maven, which might cause trouble with F-Droid (specifically with Reproducible Build)