search

Benjamin-Loison / android

0 stars 0 forks source link

Vocal assistant #28

Open Benjamin-Loison opened 6 months ago

Benjamin-Loison commented 6 months ago

For temporary use-cases:

  1. To pause/resume audio, go to the previous/next audio.
  2. To reduce/increase volume.
  3. Remind destination (sometimes have doubts as take an usual path, see Benjamin-Loison/organicmaps/issues/24)/Stop itinerary (OrganicMaps)
  4. Send a message on Signal/Element/WhatsApp/SMS/Discord (decreasing preference order, possibly contacts not having the given plateform and the plateform possibly not easily programmable)
  5. Take personal notes to not forget
  6. Be able to go back or forward of a few seconds to replay or skip multimedia segments
  7. Say that there are notifications and if asked to do so read it (Calendar reminders as Signal messages)
  8. Make a Signal call
  9. YouTube SponsorBlock skip to highlight
  10. Power on/off phone Bluetooth and connect to device
  11. Search a YouTube video (maybe not necessarily the first result)/TV channel
  12. Start and stop tracker or similar, any script that can be proceed to multiple actions
  13. Stop the vocal assistant (may be a security issue but as speaking over it can also be one may not be that much a securiry issue)
  14. Lock screen (unlocking it would be a security issue)
  15. Send an email
  16. Start a given duration timer

Can use Termux and Whisper to do so but may have load issue, could make one of my server execute the speech recognition but then pay attention to security/privacy issues.

Investigate www.home-assistant.io.

The relative being:

-----BEGIN PGP MESSAGE-----

hF4DTQa9Wom5MBgSAQdAU6WZg6bs54P2ZAMgpUYJA08QpSoFjU7k1GTQh4klRxMw
FYWnZNFF81Jj2CtzoYEyY332Y7FL74/dD3WGjwdqUNWfIHi68I5G1a5ovMAx89cb
0kABeFwAuqEVfLupb9YKCatUcRpV32o2/H7OTZSOzVMoT/+GDsUgbWNFN3VsOcO2
oh6pPNma0X9TPC5w025qSuTs
=isKD
-----END PGP MESSAGE-----

Related to Benjamin-Loison/firefox-android/issues/16 and Improve_websites_thanks_to_open_source/issues/154.

+80

Benjamin-Loison commented 4 months ago

To reduce workload may work like other well-known vocal assistants using a common prefix like Dis Siri or Ok Google. It may reduce workload by only listening carefully once have pronounced this prefix which may be detected in a more approximative fashion (note that can run precise listening to treat again the recorded prefix to make sure that it is not a false positive). The prefix could be Dis Termux. Should play a sound once have quickly or/and carefully detected the prefix to start speaking more precisely or depending if already listening with high quality but not parsing speech, then can not have such a sound, hence a delay to start giving an order.

Benjamin-Loison commented 3 months ago

Related to:

-----BEGIN PGP MESSAGE-----

hF4DTQa9Wom5MBgSAQdAPNH8MtM2jl4DOkkZc+AAXH7qLVNb09NIi1rHzz2LnXsw
YOauJPpJtUjmHLZYEk4OS1TygkPDLfr2goKM79+RLJk9MgAvP5yGfDgRiPjG3c7K
0nsBqkaba+vedDP9SIQV5u/H+MdlQFKil387YOAXGcBVwJnCCjD8CBBcia7cryaa
CknUNbGx/OvwT2znfFg8ha+Jcdn2oS8u+orVwnvF1Y8/kcpSNtOwRwXZ9Pa7l1zh
6GoUOVAQ+AqjSOgvWTBFZefW1JEXD77/dpgFOhU=
=32qL
-----END PGP MESSAGE-----
Benjamin-Loison commented 2 months ago

Related to:

-----BEGIN PGP MESSAGE-----

hF4DTQa9Wom5MBgSAQdA4lra9Ow79biS9ICHiKLa8gvmHX/cL6Zp9mg2k+5/9Wow
KFYYSlvoCZ3S+3HpQpyUB4lUhJwxp9ktfkTFDYzHfxbuGTsIyXIGCfW+PVqlOmDf
0nsBmwPvqLLnM7dgUn63PgZ2jol+S6PKzthd2tTNMp0Qtx4PT3kIQdsfwSjGR7Hu
jKMA8Y7cYlP7wmLRGbIGSGgCT14ts4GUr3eZXWp7jXq6lx4pxqh1YKCZg4y+t+yl
I9Hm96pvURQrcQb4wCPnUKhKtkZJN2Kvxxppoi0=
=0T6H
-----END PGP MESSAGE-----
Benjamin-Loison commented 2 months ago

Maybe if there is an audio being played can subtract it somehow to the audio recorded with the microphone.

Benjamin-Loison commented 2 months ago

Related to Benjamin_Loison/mobicoop-platform/issues/26.

Benjamin-Loison commented 2 months ago

Related to Benjamin-Loison/cinnamon/issues/66.

Benjamin-Loison commented 1 month ago

whisper_mic (690 stars) Source: whisper/discussions/75

looks interesting and there is no much code so can review it. Only pyaudio looks suspicious in requirements.txt:

whisper_mic/blob/8e700b75a152ee36db5fdd16af125cea8f9843a8/requirements.txt#L7 Except above requirement, whisper_mic/blob/8e700b75a152ee36db5fdd16af125cea8f9843a8/pyproject.toml looks legitimate.

Have not checked other files yet.

able (38 stars) looks less interesting.

Benjamin-Loison commented 3 weeks ago

Related to Benjamin-Loison/termux-app/issues/{37,38}.

Benjamin-Loison commented 3 weeks ago

Related to Improve_websites_thanks_to_open_source/issues/946.

Benjamin-Loison commented 3 weeks ago

Related to Benjamin_Loison/Food/issues/44.