Michael Hansen

Mixing English and Arabic sentences won't work unfortunately :slightly_frowning_face:

Hi @Jacob-Bishop, thanks for your feedback! Minimally, I think being able to stop all playing audio with a message is quite useful. Your approach of using Popen sounds reasonable, and...

Hmmm...there should be an error message sent on `hermes/error/asr` at least. I can look into the behavior of the dialogue manager more with regards to start/stop listening messages. If I...

Thanks for the write-up, @Daenara I added some more options for silence detection in 2.5.9 using the debiased energy of the audio signal. It might help, but I may need...

I've uploaded a fix in `master`, but haven't re-built the Docker images yet.

I've pushed an update to `master` that adds an option to synthesize lines separately or as one. I haven't had time to re-build the Docker images yet, though. You may...

See https://github.com/synesthesiam/docker-mozillatts/issues/17

Hi, @MarkinBrisbane. Thanks for giving it a try! I've tried and (so far) failed to build PyTorch without AVX instructions. I thought I had succeeded originally because the `-noavx` versions...

I've migrated to [Coqui TTS](https://github.com/coqui-ai/TTS), the successor to Mozilla TTS. The new Docker images are available here: https://github.com/synesthesiam/coqui-docker/ (still using the default Flask server, unfortunately). My [Larynx TTS](https://github.com/rhasspy/larynx) project is...

Hi @Bharath-Kumar-3231, this is a good question. I originally did the "intelligent" split on phonemes, but had problems when the system using gruut needed them split differently -- for example,...