The pre-training model does not support Chinese.

[v3ucn]

The pre-training model does not support Chinese.

[shirubei]

Same here.

using metadata like line below, 13000 steps but still failed to produce Chinese voice.
It's just like noise or something .

processed_1.wav|Character1|ZH|好運不會在人家等候的那個地方自然來，而是經過彎彎曲曲，與困難的難以想像的道路才降臨的

[shirubei]

翻看其他帖子，#66 说底模是英文的，似乎训练不了中文模型

[MujiKemp]

It would be better if they provide more ckpts in PRETRAINED_MODELS in download_utils.py, then select based on language. Or a super big D/G/Dur for all languages...

[anye1235]

训练代码异常：
安装readem里的训练数据格式 metadata.list的格式为：processed_1.wav|Character1|ZH|好運不會在人家等候的那個地方自然來，而是經過彎彎曲曲，與困難的難以想像的道路才降臨的

但是code里的 data_util.py _filter函数解析 _id, spk, language, text, phones, tone, word2ph = item；里面的phones 是否跳过的逻辑。导致解析错误，如果metadata.list里增加 phones, tone, word2ph空字符也是有问题，还请补充