Xueyao Zhang
Xueyao Zhang
Hi @ErLongHuDaoGe , you need to replace the `[M4Singer dataset path]` as the real path of your downloaded M4Singer dataset path.
Hi @ErLongHuDaoGe, if you have any further questions, feel free to re-open this issue!
Please use black to format your code. For example, to format a file named `wrong_format.py`, you can run: ``` pip install black black wrong_format.py ```
Thanks @ArkhamImp a lot to integrate our first VC model. For the "New Feature" PR, the review stage is more strict and usually takes several request-change loops. You can follow...
Hi @happysalada, thanks for your constructive advice! We will prepare one in these days, @yuantuo666 and @Lokshaw-Chau will follow up it. Hope we can finish it in next week 😄
Hi @c469591 , is the whole duration of your training data is just 15-30 min? If so, it is indeed difficult to learn a good model. You can utilize the...
Hi @c469591, if you have any further questions, feel free to re-open this issue. We are glad to follow up!
@ILG2021 Thanks for your attention! We have tried the multiple content features strategy on different base models, including diffusion models and SoVITS. Some results can be found [here](https://arxiv.org/abs/2310.11160) (Table 4a).
Hi @songweionline, would you describe your trouble more specific, such as attaching some running commands and errors report? Thanks for your advice about Colab. Actually we are planning to integrate...
Hi @Nugine, thanks a lot! We will patch it soon (cc @Adorable-Qin )