Dhonam Pemba

JNI Wrapper

6

Is there some code or instructions on how to call the online2-wav-nnet3-latgen-faster and build your own apk that uses the compiled android kaldi binaries? https://github.com/ahmetaa/kaldi-jni https://github.com/keenresearch/KeenASR-Android-PoC https://github.com/Kidsense/Vocally

Fine Tuning

47

Do you have the procedure for fine tuning the model with our own data? Would we use this model https://github.com/daanzu/kaldi-active-grammar/releases/download/v1.4.0/kaldi_model_daanzu_20200328_1ep-mediumlm.zip or https://github.com/daanzu/kaldi-active-grammar/releases/download/v1.4.0/vosk-model-en-us-daanzu-20200328.zip then apply this script and update the paths?...

network.xconfig for kaldi_model_daanzu_20200328_1ep-mediumlm

1

Do you have the network configurations for this model? Is it? ``` cat

simple demo

4

Do you have a simple demo, like the one in dragonfly that doesn't require dragonfly? I just want to transcribe an audio file with grammar weights added to the language...

AttributeError: module 'pyAudioAnalysis.audioTrainTest' has no attribute 'feature_extraction_train'

cloudwalk tech, the facial imagining company claims Pyramidal-FSMN, 2.97 percent,

1

http://www.ecns.cn/business/2018-10-30/detail-ifyzfmpy6337487.shtml

Build APK on Smart Phone

1

I would like to integrate the google assistant in my own app, for example have avatar be able to act as google assistant, what do we need to do different?

Increase RTF for offline transcription

1

Is there a way to just do whole file upload and decode instead of streaming real time decoding? Trying to use this system for offline transcriptions but want to speed...

No Recognition Period when starting recognizer

1

There seems to be a short time period about 3 seconds where there is no recognition ability between stoping the mic and starting it. For example as soon as you...

What is the difference between the two models?