Daniil Robnikov

Just follow the instructions here: https://github.com/macfuse/macfuse/wiki/Getting-Started It helped me from start to finish

I have found this topic, where author discusses KL divergence in detail: Please refer: [#6](https://github.com/jaywalnut310/vits/issues/6)

Hi, @paperr0se ! Not yet. Currently I am working on multilingual support based on conditioning on language. I plan to test it on German as well, so if you `have...

Good to hear! Keep me in touch, in case you find anything valuable

Yes, the model supports 3 Accents/Dialects of Chinese, namely: - Mandarin - Hakka - Cantonese To use one of these languages, you need to: 1. phonemize your text with open...

Good question! I haven't tested the model on Chinese dataset yet. At this point, I have trained the model on LJSpeech dataset for 18k steps out of 800k, and here...

Thanks for sharing the code, I would greatly appreciate any support. Also for cn lexions in Chinese, it is required to have multi-character tokenizer, as initially vits supports only by-character...

Heads-up on the Chinese support: I have updated configs to include language param. All you need is to assign the language identifier (found in [here](https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md)) to the `language` ```yaml data:...

As far as I understand, for Mandarin-Chinese you would use `cmn` identifier: ```python from phonemizer import phonemize text = "语音合成技术是实现人机语音通信关键技术之一" phonemes = phonemize(text, language="cmn", backend="espeak", strip=True, preserve_punctuation=True, with_stress=True) print("text: \t\t",...

I see, so for Chinese language it is way more complicated. As I understand, in context of Speech Synthesis, using phonemizer or any other g2p conversion is just bridge to...