keenresearch / keenasr-android-poc Goto Github PK

I can see this app works in small sessions and then stops listening after i stop speaking for a second. Is it possible to get it work for a longer period of time - like application listens for my commands and responds with something and continue to listen (on your site it it said it can be used for Voice control in apps,
Circumvent complex navigation)? I feel like there should be a way, just not sure how to do it.

I have built a POC following the documentation. Here is what I am facing.
The app runs smoothly inside the activity when running for the first time.
When I go to some other activity and come back, the recognizer returns two final results for the same word.
For example, it gives ["final"] and ["final"] as a result when I speak "final".
i:e onFinalResult is called twice for every result.
Now if I again go to some other activity and come back, the onFinalResult is invoked three times every time I speak, and this cycle repeats.

com.keenresearch.keenasr_android_poc A/libc: Fatal signal 11 (SIGSEGV), code 1, fault addr 0x0 in tid 21381 (AsyncTask #1)

WARNING: AUDIO BUFFER OVERFLOW!!! -- decoding speed is slower than real time (this is a problem) CB.size: 17280, CB available: 2560, new bytes: 3200

Taken from logcat.

Also I see to get results as "<SPOKEN_NOISE>" and "Num words", not sure if this was intentionally. How Keen to give me English STT results?

Thank you for the help

how can I obtain a version of the KeenASR-Android-PoC
without 15min's limitation?

I've been trying for a while but I'm not sure as to my solution is good in terms of performance.
BTW, is there any Spanish acoustic model?

Hi, i've tryed your PoC for unity, when i build to my android device i get the "KeenASR SDK was not initialized properly", but i couldnt found what's the problem.

Could your give some help to make me know if your plugin is what i required for my app?
thanks.

Device : galaxy S8
Android 9
Unity 2019.2.3f1