genie-toolkit
genie-toolkit copied to clipboard
The Genie open source kit for voice assistant (formerly known as Almond)
AST manipulation methods are tricky and full of corner cases. Testing by generating sentences is not exhaustive, unless we run at high depth and high pruning size, which takes too...
It seems to be invoking the Python script for every single sentence to autoparaphrase, which causes the model to load from disk and initialize, and doesn't take advantage of sentence...
Device discovery was removed from thingengine-core when it was merged here, because the dialogue loop cannot be represented well in terms of ThingTalk code.
Currently the agent will pick one, two or three results from the top of the list (depending on the parameter priority and some randomness in pruning). It would be nice...
Our system should allow developers to specify non-textual content in the replies from the agent. For speech, we should support sound effects, emphasis, prosody. We might want to target [Speech...
Entity strings in the sentences are not quoted when generating mturk inputs.
That's it. That's the bug. Nothing will work until we have a decent wakeword. The current one is just bad.
On a Raspberry PI, echo cancellation is so CPU intensive that PulseAudio can hit buffer underruns, which cause audible cracks in playback.
This is the close cousin of https://github.com/stanford-oval/thingtalk/issues/231 Of course, at first turn the work is basically done, because it is already working in single-sentence datasets, but we should be able...