Issues
- 0
Audio sample distribution visualization
#188 opened by dimuthuanuraj - 0
Multi node training
#187 opened by ukemamaster - 6
How can I get the USERNAME and PASSWORD?
#184 opened by DiLiangWU - 6
Dataset download
#176 opened by yuelei0428 - 2
Dataset cannot be downloaded
#177 opened by zoroglu - 1
Missing Voxceleb1 Identification Dataset
#182 opened by Xiang47 - 6
the url for data download can't work
#171 opened by LeeHongji - 1
How to train used DINO framework
#175 opened by TingziGITHUB - 1
No Video Version of VoxCeleb1
#178 opened by CloudWalkerW - 0
test/train_list format
#186 opened by shreeshailgan - 0
Variability in Score Values Generated by Pretrained Model during Evaluation
#183 opened by dimuthuanuraj - 0
- 3
Why the speed is very slow?
#180 opened by dimuthuanuraj - 2
Shouldn't Prototypical loss use torch.cdist instead of F.pairwise_distance?
#169 opened by theolepage - 1
Issue with training Common Voice Dataset
#170 opened by dimuthuanuraj - 0
- 4
- 7
Need new download script
#159 opened by brianw0924 - 0
- 2
Use as Speaker Encoder for 48kHz audio
#138 opened by astricks - 0
How to change the sample rate?
#173 opened by predawnang - 1
ValueError: Conversion failed
#164 opened by KajiMaCN - 0
how to save a new pretrained model
#172 opened by dntuong - 0
What validation data is using?
#168 opened by katsu-77 - 1
training RawNet3 with new dataset
#158 opened by angelabr - 1
Data preparation
#167 opened by shiddiqie - 0
A bug in convert function path
#165 opened by griko - 3
Data preparation
#163 opened by mattymz - 2
Download Speed
#161 opened by simasima121 - 1
Video Dataset of VoxCeleb2
#152 opened by testzer0 - 1
- 1
Issues with pretrained model `RawNet3/model.pt`
#157 opened by SangwonSUH - 3
Where is the DINO self-supervised framework?
#155 opened by speaker-lover - 3
Question about angleproto.py code
#146 opened by huangrunqian - 1
RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int
#148 opened by muzihuole - 1
Error in evaluateFromList() from SpeakerNet.py
#150 opened by gems047 - 3
Is there anynone tried large margin finetune?
#135 opened by llearner - 1
How to calculate the test accuracy?
#137 opened by dairuining - 1
- 1
The pretrained model of VGG
#147 opened by muzihuole - 1
Inquiries on multi-modal data loader
#151 opened by ClaudiaShu - 12
- 1
- 0
GAN based losses.
#153 opened by dimuthuanuraj - 6
Question regarding dataset downloading
#149 opened by itsmag11 - 2
question on the pretrained models
#145 opened by jkhourybbn - 1
Can't unzip the folder
#141 opened by ShayKaiserman - 2
- 2
torch version for using 'all_gather_object'
#139 opened by msh9184 - 3
How to test with a different test list?
#133 opened by dimuthuanuraj