jefflai108/Contrastive-Predictive-Coding-PyTorch
Contrastive Predictive Coding for Automatic Speaker Verification
PythonMIT
Issues
- 1
NCE accuracy calculation
#14 opened by JaejinCho - 0
About negative sample?
#16 opened by aceprojectx - 0
NCE should be calculated for each output of the GRU (and future positions) instead of only a random index
#21 opened by Ieremie - 0
Use of Batch Normalisation
#20 opened by Ieremie - 0
Softmax uses by default dimension 1
#19 opened by Ieremie - 1
Feed entire input to encoder??
#17 opened by NeteeraAF - 1
Train and test data not available
#10 opened by martinmamql - 2
What is the format of "list" file?
#9 opened by couragelfyang - 5
Some Trouble in Understanding
#5 opened by cyl250 - 0
- 1
Hey should 'correct' only be if the final prediction was correct? Same for accuracy?
#15 opened by colinator - 1
- 0
Train the spk_class.py
#12 opened by super-wcg - 0
why torch.diag in nce loss?
#11 opened by artificertxj1 - 3
Can you provide the train & test dataset?
#1 opened by guanyuelee - 1
The implementation of loss might be wrong
#7 opened by aayushP - 3
how to format h5 files for input?
#8 opened by kachiem - 1
Threre might some wrong in validation.py
#6 opened by cyl250 - 2
- 4
How combine MFCC and CPCfeatures
#3 opened by cyl250 - 1
Code question in src/model/model.py#L113
#2 opened by joeyy5588