mimic2
mimic2 copied to clipboard
Text to Speech engine based on the Tacotron architecture, initially implemented by Keith Ito.
First thanks for author's work. I exprot the saved_model with the export.py. And I want to deploy this model with tensorflow serving and use the rest api to make the...
TTS-Cube
What is the inference time of Tacotron model used in mimic2 in low footprint devices such as rasperry pi for say 10sec of audio? Looks like there is another TTS...
Hi there currently with the american male when words are capitalized they are spelt out.. which is annoying for my book/document reader in the real world not many words are...
I wonder if this is the repo which is cloned as a submodule by mycroft-core and built for its offline mimic functionality
Hi again, I've trained the model up to 89,000 steps. It is close to getting aligned, but is still not quite there. The problem is that it has been pretty...
Use manual from main page. How solve it? ``` root@508f20df7aee:~/mimic2# python3 preprocess.py --dataset ljspeech /usr/local/lib/python3.5/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In...
… and improved docker image to reuse pip install
So I've been trying to train this on the LJSpeech data set since it seemed like the most solid one out there. However I've been having an issue where there...