issues
search
clovaai
/
voxceleb_trainer
In defence of metric learning for speaker recognition
MIT License
1.01k
stars
272
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Use as Speaker Encoder for 48kHz audio
#138
astricks
closed
2 years ago
2
How to calculate the test accuracy?
#137
dairuining
closed
2 years ago
1
Reduce data waste with "resmixid"
#136
IMLHF
opened
2 years ago
0
Is there anynone tried large margin finetune?
#135
llearner
closed
2 years ago
3
Short speech(< 1 sec)bad performance,how to improve?thanks!
#134
sundyll
closed
2 years ago
1
How to test with a different test list?
#133
dimuthuanuraj
closed
2 years ago
3
How you generate speaker embedding?
#132
dimuthuanuraj
closed
2 years ago
5
what is the mean TEER/TAcc?
#131
sundyll
closed
2 years ago
2
Different batch sizes will yield different performance results.
#130
rezimitpo
closed
2 years ago
2
The password and username
#129
harlanhong
closed
2 years ago
3
Is speech/voice activity detection a part of this implementation
#128
iiscleap
closed
2 years ago
2
Update download links
#127
ngoanpv
closed
2 years ago
1
Must the datasets convert to wav from m4a?
#126
sundyll
closed
2 years ago
1
training is extremely slow (single gpu v-100, ssd)
#125
zabir-nabil
closed
2 years ago
2
Download script has some error?
#124
ali2iptoki
closed
2 years ago
4
Lossfunction issue
#123
makimon123
closed
2 years ago
4
Train list & Evaluation list
#122
dimuthuanuraj
closed
2 years ago
2
Difference between speakerNet and speakerNet of NIVIDIA?
#121
ali2iptoki
closed
2 years ago
2
how to regist the person voice and predict it by new wav file
#120
daizzhisheng
closed
2 years ago
4
SpeakerNet: score = -1 * numpy.mean(dist)
#119
zengxinch
closed
2 years ago
1
How to find the optimal threshold?
#118
ukemamaster
closed
2 years ago
4
dataset problem
#117
yaoyao1206
closed
2 years ago
4
get error when use --mixedprec get
#116
jingxuan9862
closed
2 years ago
2
import nsml
#115
zengxinch
closed
3 years ago
1
What are the exact versions of all the dependencies given in the requirements.txt file?
#114
ukemamaster
closed
3 years ago
1
why use negtive as positive in triplet loss
#113
WilliamZhaoz
closed
3 years ago
0
triplet 等其他loss的training的code和命令求补充
#112
WilliamZhaoz
closed
3 years ago
1
Dataset download
#111
CaptainPrice12
closed
3 years ago
2
Training slows down after few steps
#110
ukemamaster
closed
3 years ago
2
Issues when trying different loss functions
#109
SaniyaAbushakimova
closed
3 years ago
3
Training the baseline only
#108
ukemamaster
closed
3 years ago
0
difference between wavfile and soundfile?
#107
seacj
closed
3 years ago
3
what does the id mean?
#106
SiyuanWei
closed
3 years ago
1
how to calculate multiplyaccumulate operations
#105
Tianchi-Liu9
closed
3 years ago
2
Distributed
#104
joonson
closed
3 years ago
0
Index error
#103
BakingBrains
closed
3 years ago
1
Pre-trained model unavailable
#102
CaptainPrice12
closed
3 years ago
2
Distributed
#101
joonson
closed
3 years ago
0
Similarity or distance metric to calculate scores?
#100
Nada-gh
closed
2 years ago
2
Pre-trained model files linked in the readme are not accessible anymore
#99
vickianand
closed
3 years ago
1
Q: distribute training doesn't seems to split dataset between GPUs
#98
asimov-aiz
closed
3 years ago
4
About the changing training data sample rate
#97
whitegon
closed
3 years ago
2
about GRAPH ATTENTION NETWORKS FOR SPEAKER VERIFICATION
#96
seacj
closed
3 years ago
0
Question about converting to TensorFlow
#95
navid-a
closed
2 years ago
1
questions about dimension transform
#94
forwiat
closed
3 years ago
1
Bug with Multi gpu training
#93
009deep
closed
3 years ago
8
question about data transpose in SpeakerNet.py
#92
forwiat
closed
3 years ago
1
Res2net model support
#91
stevenhillis
closed
2 years ago
2
The configuration of HA4 in paper
#90
llearner
closed
3 years ago
4
Training difference between 2 work
#89
009deep
closed
3 years ago
9
Previous
Next