Alok Prasad

Depends on the platform ? Its not Tacotron2 is not realtime yet, but if we are able to compile libtensorflow-core.a for Android using ndk16 or above ( rather than ndk14b)...

i dont have 1080 , so haven't done inference on it.

@MlWoo will wait for the changes , meanwhile will try myself .

@MlWoo Thanks for the patch , will try and update you.

So while training tacatron2 , i should replace/softlink the f32 to audio folder of training_data( after preprocessing) and train.txt first column(meta[0]) should be actual name of f32 files right? if...

@superhg2012 replace the f32 created to audio folder.. check this diff based on Mlwoo changes. https://github.com/alokprasad/LPCTron/blob/master/Tacotron-2/Tacotron2-lpcnet_changes.diff

@superhg2012 Please find the recording,,( They are not good) I think we should retrain lpcnet with f32 generated from tactron2 https://vocaroo.com/i/s1Dx9nbKFeuY https://vocaroo.com/i/s1VRBWayVzrD

@MlWoo do you mean that each Audio file should be of same length or it should in integral multiple of frames?

@MlWoo Can you point to code in LPCNet , where the modification need to be done.

@MlWoo i saw that https://github.com/mozilla/LPCNet/commit/554b6df65eca11f572e4a7d3b266f54a37a4a17f there is silence removal here, and this is needed only to during training of LPCnet . Should i remove this code and Train LPCNet.