<\/div>\n <\/div><\/figure>\n\n\n\n
Click Train<\/strong><\/p>\n\n\n\n\n\t\t\t\n\t\t\t\t \n\t\t\t<\/svg>\n\t\t<\/button> \n
\n <\/path><\/svg>\n <\/button>\n \n
<\/figure>\n<\/div>\n \n
<\/figure>\n<\/div>\n <\/div>\n <\/div><\/figure>\n\n\n\n
At Enter the experiment name<\/strong> Enter a name there without spaces. It is recommended to use Pinyin or English. It can be the name of the character you train.<\/p>\n\n\n\nIt is enough to select 40k as the target sampling rate. If your sound data has 48k, of course 48k is better for training.<\/p>\n\n\n\n
I recommend checking ture<\/strong> for pitch guidance whether you use this model to sing or not, because people usually speak differently.<\/p>\n\n\n\nIt is recommended to keep the default number of CPU processes. If you are confident in your hardware, you can increase it or increase it to full.<\/p>\n\n\n\n
Then Shift + right-click on your training data folder Copy as path<\/strong><\/p>\n\n\n\n\n\t\t\t\n\t\t\t\t \n\t\t\t<\/svg>\n\t\t<\/button> \n
\n <\/path><\/svg>\n <\/button>\n \n
<\/figure>\n<\/div>\n \n
<\/figure>\n<\/div>\n <\/div>\n <\/div><\/figure>\n\n\n\n
Then paste it into Enter the training folder path<\/strong> Don\u2019t touch anything else<\/strong><\/p>\n\n\n\nThen choose the model that handles pitch, I recommend using rmvpe_gpu if you have multiple graphics cards you can follow the instructions to change it<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\t \n\t\t\t<\/svg>\n\t\t<\/button> \n
\n <\/path><\/svg>\n <\/button>\n \n
<\/figure>\n<\/div>\n \n
<\/figure>\n<\/div>\n <\/div>\n <\/div><\/figure>\n\n\n\n
Then slide down to the last column<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\t \n\t\t\t<\/svg>\n\t\t<\/button> \n
\n <\/path><\/svg>\n <\/button>\n \n
<\/figure>\n<\/div>\n \n
<\/figure>\n<\/div>\n <\/div>\n <\/div><\/figure>\n\n\n\n
The first item Save frequency<\/strong> can be kept as default, so that you can continue training even after the computer is powered off and restarted. Of course, if you are confident, you can also save it directly after 50 rounds.<\/p>\n\n\n\nTotal_epoch can be kept as default. Generally, the default is enough to clone the timbre. However, if your timbre is special (such as clip tone), it can be increased to 200, but the training time will also increase. In theory, the higher the Batch_size, the faster the training. At the same time, It also takes up more and more existing resources. If the GPU performance is poor but the video memory is increased, the model quality will decrease.<\/p>\n\n\n\n
It is recommended to keep the latter options unchanged. If your hard disk space is insufficient, you can check to only save the latest ckpt.<\/p>\n\n\n\n
Then click One-click training<\/strong> to start training. It is recommended to close all other web pages and background programs. Only keep the current page and backend. Do not close the web page. Wait for the training to complete. You will be in the Installation directory\/\\ Find training name.pth<\/strong> under assets\/\\weights<\/strong>. This is your model file and then find in Installation directory\/\\logs\/\\training name<\/strong><\/p>\n\n\n\nDone<\/h4>\n\n\n\n Next, please enjoy the model you trained. If you are willing, please share the model with more people. It is recommended to upload it to Hugging Face<\/a><\/p>","protected":false},"excerpt":{"rendered":"\u524d\u8a00 \u5728\u5f80\u671f\u6587\u7ae0 \u4e00\u4e2a\u53e6\u7c7b\u7684RVC\u5b9e\u73b0\u65b9\u5f0f – Arasaka ltd. \u4e2d\uff0c\u6211\u7b80\u5355\u4ecb\u7ecd\u4e86RVC\u53d8 […]<\/p>","protected":false},"author":1,"featured_media":196,"comment_status":"open","ping_status":"open","sticky":false,"template":"single-with-sidebar","format":"standard","meta":{"_seopress_robots_primary_cat":"","_seopress_titles_title":"","_seopress_titles_desc":"","_seopress_robots_index":"","footnotes":""},"categories":[11],"tags":[25,26,21,17,16,19],"_links":{"self":[{"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/posts\/177"}],"collection":[{"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/comments?post=177"}],"version-history":[{"count":5,"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/posts\/177\/revisions"}],"predecessor-version":[{"id":278,"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/posts\/177\/revisions\/278"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/media\/196"}],"wp:attachment":[{"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/media?parent=177"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/categories?post=177"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.arasaka.ltd\/en\/wp-json\/wp\/v2\/tags?post=177"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}