zhouwg / kantv

workbench for learing&practising AI tech in real scenario on Android device, powered by GGML(Georgi Gerganov Machine Learning) and NCNN(Tencent NCNN) and FFmpeg
Apache License 2.0
117 stars 19 forks source link

UI:enable APK user download user-specified GGML model file and use user-specified model file to do online-TV transcription #78

Closed zhouwg closed 6 months ago

zhouwg commented 6 months ago

Looks Good To Me after validation with 10+ cases (4 -- in ASRResearchFragment.java + 2 -- in realtime subtitle + 5 -- in ASR Setting) in 3 different scenario on Xiaomi14

zhouwg commented 6 months ago

this PR also fix the below bug during switch to Project Whispercpp-Android:

UI in ASRResearchFragment.java can NOT works properly as expected. because original/non-modified whisper.cpp was used in last commit.