Alexander Veysov

After fixing the concat bug, I managed to convert my model. The whole model gives reasonable discrepancy (sotmax being the last layer), but I still suspect it is not enough...

> How are you using a IlgSimplifiedNormalized class? Please see the snippet below. Inception4Cadene - is just the above inception4 original code. IlgSimplifiedEnsemble - is just the above model. ```...

Also please note that this is just a `V1` release, models will be much faster in future

We just base our models off PyTorch and / or ONNX As far as I know there are no actively maintained node-js bindings for PyTorch There are though for ONNX,...

Internally in such cases (where the controlling app and the inference engine are not the same) we just use rabbit-mq communication with a model in a separate container

Please see this article - it has plenty of audios - https://habr.com/ru/post/549482/ Or just use the colab - https://colab.research.google.com/github/snakers4/silero-models/blob/master/examples_tts.ipynb Since we do not have web developers, we do not active...

Hi, I could not really understand from their example where / how the actual speech synthesis is run / stored There is an example code here - https://github.com/mdn/web-speech-api/tree/master/speak-easy-synthesis - but...

@SeanNaren would be really great if you could help out with this @adamnsandle Which tokens do you use, how much data do use to train the model, how do you...

@adamnsandle Also which kenlm command did you use to train an LM? @SeanNaren Which command do you use for your models?

@lmcinnes I do some stuff with high level CNNs with Pytorch (best library for GPU + CNNs). I found your library and education materials in the docs amazing. Probably if...