The library of Chinese grapheme-to-phoneme conversion is not complete. I have found part of missed Chinese words: 邓,吴,鄂,皖,蔡,萨,廖,宋,秦,刘,滧,闫,陕,郑,郝,犇,鹏,陇,祾,渭,邹,濮,梵,佟,韩,龚,洛,湘,婍,沂,隋,洣,潘,蒋,禹,喲,闽,湳,綪,睍,孻,汶,杭,…
Hi, I'm going to re-raise the topic in #12, which is currently closed. I apologize, and I appreciate that this is in some sense bad form.
I also would like the ability to, occasionally, fine-contr…
Continuation of clarin-eric/LRSwitchboard#55, quoting @andmor-:
> @proycon sorry looks like everyone forgot to follow up on this.
No problem, so did I, hence this late report.
> Yes all web se…
I have trained the teacher model from the scratch with 14900 utterances ~ 40 hours on the Vietnamese dataset.
The model takes about 30 minutes for an epoch with GPU V100 32G VRAM and batch size = 64.…
The piper-phonemizer setup is a bit confusing at the moment as it's both a included with some significant code and a library imported at runtime. The two phonemizers text and espeak are both tightly …
I have placed the model in vc/models/ and executed WebUI. I can select the model name in Voice Conversion. However, when I click on 'Generate From Text', the following error appears and no audio is cr…
```
While stopping the playback using an eSpeak voice works well, you cannot stop
the playback when using an mbrola voice – the Gespeaker application just
»freezes« (and even turns »dim« if the text…
The readme makes it sound very simple: "Replace bert with xphonebert"
Looking a bit closer looks like it's quite a feat to make StyleTTS2 talk in non-english languages (https://github.com/yl4579/Styl…
Hi,
When I use allosaurus with the eng2102 model for an English wav file, the results looks quite good (although there is one issue, if there is no silence at the beginning of the wav file, some ph…