Adrien Ball

@ak-nv, It's quite hard to debug this issue on our side as we cannot reproduce your build environment (no Jetson board here), and the stacktrace suggests that the issues is...

Also, latest rust version is now 1.34.1 so it may be worth updating.

Hey, thanks for the feedback, It is a reasonable use case indeed. We will add the support for it as soon as we can. It shouldn't be too hard. Best,...

Hi @laboitemail , If you plan to use Snips on a raspberry pi, you should rather have a look at the [Snips Platform documentation](https://docs.snips.ai/getting-started/quick-start-raspberry-pi) and also join the [forum](https://forum.snips.ai). Using...

Hi @gembin , The training is done with the python library [snips-nlu](https://github.com/snipsco/snips-nlu), see the documentation [here](https://snips-nlu.readthedocs.io/en/latest/). Once you have trained an NLU engine, you can load it and run the...

@gembin Implementing the training in Rust is something we have been discussing internally for the past months. It would have many advantages in terms of packaging and release process. However...

Hi @gembin , apologize for the very late answer, your issue somehow got lost. This rust library works on atomic elements, named tokens. It is indeed targeting inputs which are...

@Psychokiller1888 Can you confirm that you have selected Google ASR on the web console? The reason why I'm asking this is that the verbalization that you see on the console...

The issue is that the NLU pipeline has a specific configuration for each ASR engine (Snips, Google). These configurations are adapted to the ASR output. Hence, for Snips ASR, the...

@Psychokiller1888 I found out the root cause of your issue. The `+` symbol, as well as most of the symbols, is tokenized out internally in the NLU, meaning that `"hello...