Michael Hansen
Michael Hansen
@arturpragacz After more thought and discussions, we don't plan to move forward with this. While I agree with your points about code organization and responsibility, the added maintenance burden of...
You may need to configure Ollama to listen on all network interfaces: https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server By default, it will only listen on 127.0.0.1
> I believe most or all of those are trained on synthetic data I think they all are, which has worked out well for [openWakeWord](https://github.com/dscripka/openWakeWord) because it uses a pre-trained...
@farooqkz I'd love to continue the discussion, but this is not possible with Stuart present. He has received numerous warnings, and is no longer welcome in the Home Assistant community....
Thanks for putting this together! I'm especially interested in the weights initialization and extra control for fine-tuning. For the future of this codebase, I'm splitting out an espeak-ng only version...
This was actually fixed last week, so it will be in the next release :slightly_smiling_face:
Sounds like it's trying to run two copies of the add-on.
Alignment data is obtainable from the original PyTorch models, but not the Onnx models currently. This would require re-exporting all the voice models (incompatible with existing Piper) as well as...
If I added this, I don't know if it would be possible to rebuild the docker images at this point.