f96189a509
Updated the processAudioLoop to mke sure that the buffer was always flushed after an output stream so we didn't miss any characters. Also made many modifications to the python script running on the Pico to ensure that we get dual inputs and neater outputs now.
StreamingPunctuation
mmanningau2026-02-09 14:48:55 +11:00
75b63f91ea
Updated to continually check for the a valid USB connection on each press of the mircophone and also totally rewrote the send to Pico code as well to me more robust...
mmanningau2026-02-03 20:39:00 +11:00
9f6d67a567
Added the debug.keystore to the repo so that I can move between devices and build the app without getting installation errors on the phone. Also updated the testModelActivity to a more robust USB connection permissions testing and connection testing....
mmanningau2026-01-30 16:40:42 +11:00
2a8f004916
Updated the AndroidManifest.xml to stop the default function exit call upon screen rotation and just have it remain inside the "startRecording" function.
mmanningau2026-01-26 15:38:34 +11:00
ac7d51b46e
ADded the punctuation sections to the code - but have not added the zip extraction to include this automatically - might ahve to add another upload manager specifically for this one file I think, as it is really messy to get your hands on through other means....
mmanningau2026-01-23 12:52:24 +11:00
f17c6ab84e
Updated to finally fix the double up text during the translastion at sometimes at the start of the second press of the microphone button
StreamingOnnx
mmanningau2026-01-23 12:24:56 +11:00
4be8da6b2c
Attempt one after major code update to implement the true Whisper model use and operation
master
mmanningau2026-01-23 10:33:31 +11:00
6471f642c4
Updated the streaming to avoid the double ups in the output...looks better now...
mmanningau2026-01-22 21:06:26 +11:00
05787d20d2
Updated and tested using the sherpa onnx streaming file - had to download it and extract from tar.bz2 and recompress as zip but that was a start....
mmanningau2026-01-22 20:58:12 +11:00
ce72ef7a16
Most changes which compile using the Whisper Sherpa setup - but prior to the changes in the MainActivity file which will unzip the new model files for us automagically ;-)
mmanningau2026-01-22 20:30:14 +11:00
404bc55ed3
Initial steps to migrate to the whisper/sherpa setup.. Still missing majot changes to the TestModelActivity.kt file which are coming next...
mmanningau2026-01-22 19:49:48 +11:00
12c0508713
Added randomly unversioned files that I thought should be included....
mmanningau2026-01-22 17:11:00 +11:00
8f178d16e9
Updated version number for test installation
mmanningau2026-01-22 17:10:15 +11:00
813441645c
Added .gitignore and updated to include the USB connection and stream on certainty of word/phrase results....
mmanningau2026-01-22 16:32:36 +11:00