mimic2
mimic2 copied to clipboard
MycroftAI
Text to Speech engine based on the Tacotron architecture, initially implemented by Keith Ito.
**Describe the bug** I'm trying to run preprocess **To Reproduce** Steps to reproduce the behavior: 1. Make steps from README.md 2. Run all in docker (cpu) 3. Model https://keithito.com/LJ-Speech-Dataset/ **Expected...
**Is your feature request related to a problem? Please describe.** The last commit of this repo dates back to Jun 8, 2020 (9fd123c), but you have the following sentence in...
Hello developers. I'm not a dev, but I am suggesting some improvements and features/ideas for this engine. First with the shorter one, to improve the quality of the voice, you...
Hey, seeing as there's a new version out for TensorFlow, and there is a [tool](https://www.tensorflow.org/guide/upgrade) for upgrading from TF 1.x to 2.x Is this something that can be done for...
Is [SSML](https://www.w3.org/TR/speech-synthesis11/) support possible with mimic2 as it is with mimic1 (or at from my understand at least partially implemented in mimic1)?
I want to assume that this would work. ''' docker build -t mycroft/mimic2:gpu -f radeon_gpu.Dockerfile . docker run -it -p 3000:3000 mycroft/mimic2:gpu ''' with main change being radeon_gpu having '''FROM...
Hi, After successful installation and process. When I try to execute the training.py, my system gets hang and I could not do any action unless force shutdown. Please assist for...
Hi, I want to train the model in French, i use the data set from website 'common_voice'. **I wrote commoncoive_fr.py like this:** from concurrent.futures import ProcessPoolExecutor from functools import partial...
Hi, I'd like to know how I could get the phonemes from the model apart from the wav file, like in the server used in mycroft-core. Thank you
Do you have some pretrained models? Besides that one, can we use Keitho's models? http://data.keithito.com/data/speech/tacotron-20180906.tar.gz https://drive.google.com/file/d/1c_O-Gha03_erKbilsFCvs9QJ8faJ7ou8/view?usp=sharing Or Zamia's models? https://goofy.zamia.org/zamia-speech/tts/tacotron/
