Lenos500

> Have you solved this problem? @Lenos500 @jbartolozzi Yeah I solved it 2 months ago by doing pip install which is listed in the comments here.

> really depends on the resolution > > but 1k images is not enough, that's for sure What if it's on the 512*512 resolution using around 2-3k images then how...

> Why not just use Whisper to transcribe and then translate in the middle? Can you tell me how to do it in details? Like step by step please?

> Following steps solved it for me: > > 1. Delete contents of `%LOCALAPPDATA%\tts\tts_models--multilingual--multi-dataset--xtts_v2` > 2. Open a command prompt in your text gen web Ui dir and run `cmd_windows.bat`...

> have you tried this one from adobe? I didn't because I don't have time, but it atleast has training and inference code with instructions 🤷

> 2 48G GPUs Oh thanks, these requirements are not consumer friendly though if someone wants to run it locally. 😂

> Exact same issue, guessing the server is down or unreachable? But isn't installation with cmake not working currently? So what's the point?

> same issue, looks like the server is down: > > ``` > ping posefs1.perception.cs.cmu.edu > Pinging posefs1.perception.cs.cmu.edu [128.2.220.57] with 32 bytes of data: > Request timed out. > ```...

> > > same issue, looks like the server is down: > > > ``` > > > ping posefs1.perception.cs.cmu.edu > > > Pinging posefs1.perception.cs.cmu.edu [128.2.220.57] with 32 bytes of...

> 又是一个阿里的假开源 Well yeah maybe, I've tried the demos they released on modelscope and they work. Also they have the paper published on arxiv, they said they'll release code on...