-
Hello.
When I tried to run the demo.py I got this error :
```
C:\deepfake>python demo.py --config config/vox-adv-256.yaml --driving_video assets/crop.mp4 --source_image assets/torsten.png --checkp…
-
hello lawlict, Thank you so much for the great work you shared.
My eer is 2.65% in voxceleb_test which can't reach to 1.*% when I training this model. I use aam-softmax loss which is same as loss men…
-
Hi,
I'm working with NeMo to find out if a particular voice belongs to a specific person, to use as authentication. I saw several issues about and tested some scripts but I don't know if I'm on the…
-
@joonson
Thank you so much for your contribution on this open source work, it really helps me a lot.
As is known to all, TNDD is commonly implemented in Kaldi.
If I want to implement it in PyTorch…
-
what about the file "vox1_meta.csv"
-
``` python
from pyannote.audio.pipelines import SpeakerDiarization
CONFIG = {
"segmentation": "pyannote/segmentation",
"embedding": "speechbrain/spkrec-ecapa-voxceleb",
"clustering"…
-
I find some errors in Voxceleb training experiments.
1. The valid error rate is 1 from the 11th epoch.
2.epoch: 1, lr: 7.46e-04 - train loss: 5.50 - valid loss: 1.56, valid ErrorRate: 4.64e-02
epoc…
-
During [evaluation](https://github.com/TaoRuijie/ECAPATDNN/blob/main/ECAPAModel.py#L82), the current implementation calculates the similarity scores one by one using a for loop, that could be slow whe…
-
Hello, I now have a question: about the training speaker embedding part, how to deal with voxceleb dataset to prepare for training? The reference you provided doesn't quite understand! thank you！
-
Hi! Thank you for the project and the codebase! I noticed that for some datasets, links to the pretrained models do not work: e.g. the image generator link on FaceForensics leads to [https://github.co…