unmesh1528

Ho do I train with my own data ?

2

Hi, Your work seems amazing. I was looking to train it for my own dataset of only one character. Can you please share detailed instructions for training ? Thank You.

RuntimeError: mat1 and mat2 shapes cannot be multiplied (4x278528 and 512x512)

6

While I run run_syncnet.py getting below error : `WARNING: Audio (3.6720s) and video (3.7200s) lengths are different. Traceback (most recent call last): File "run_syncnet.py", line 40, in offset, conf, dist...

EOFError: Ran out of input

2

> after running "run_pipeline.py", I am getting this error : `Stream mapping: Stream #0:1 -> #0:0 (mp3 (native) -> pcm_s16le (native)) Press [q] to stop, [?] for help Output #0,...

ImportError: cannot import name '_LazyImporter' from 'torchaudio._extension.utils' (/root/miniconda3/envs/voicecraft/lib/python3.9/site-packages/torchaudio/_extension/utils.py) Does anybody know how to resolve this issue ?

After training with my custom dataset, getting grey box on face while inferencing

6

I trained with my custom dataset, the dataset is quiet small with only one face. When I tried inference, I am getting a grey box on the face in video...

- When I use Mac the effect gets applied to input audio - When tried with Windows, I can see the parameters of VST3 plugin and output gets generated but...

Hi, your work seems amazing. I am looking to train for my own dataset with only one character. Can you please share detailed instructions for training ? Like preprocessing, video...