google uis-rnn issues - Githubissues

google / uis-rnn

This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.

https://arxiv.org/abs/1810.04719

Apache License 2.0

1.56k stars 319 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Is the GRU really needed to predict mu_t ?

#42 hbredin closed 5 years ago
7
The clustering performance influenced by overlap window size

#41 taylorlu closed 5 years ago
7
[Question]test on speakers untrained

#40 Aurora11111 closed 5 years ago
3
[Question] Would it be possible to publish trained models

#39 rnunziata closed 5 years ago
3
[Question]Performance degrade for different win size

#38 FengLeee closed 5 years ago
1
[Question] How to prepare embedding data for training UIS-RNN?

#37 OpenCVnoob closed 5 years ago
6
about the version of pytorch and tensorflow

#36 Aurora11111 closed 5 years ago
1
Allow `predict()` to accept a list of test_sequences as input

#35 wq2012 closed 5 years ago
0
[Invalid][Cloud] Speaker tag is not accurate

#34 balavenkatesh3322 closed 5 years ago
1
about the training loss and the batch size

#33 simpleishappy closed 5 years ago
8
Batch prediction? - or allow prediction using multiprocessing

#32 hbredin closed 5 years ago
12
Test modell

#31 monosakkarid closed 5 years ago
1
Consider making the package available in conda

#30 wq2012 opened 5 years ago
1
Performance degrade for multi-person meeting

#29 PES2g closed 5 years ago
3
Add a `online_predict()` API for streaming input

#28 wq2012 opened 5 years ago
3
Question on time cost during each iteration

#27 hcfeng201 closed 5 years ago
6
Consider allowing enforcing max number of speakers in predict()

#26 wq2012 opened 5 years ago
0
wrong diarization results for long sentence (about 60 seconds)

#25 xebro closed 5 years ago
1
Have you train the model on one database and test it on another database?

#24 wuqiangch closed 5 years ago
3
Obscurity involved in sampling rate information of datasets used

#23 ronva-h closed 5 years ago
1
Better fit() API, to accept list of sequences

#22 wq2012 closed 5 years ago
0
Dataset

#21 DenisSouth closed 5 years ago
1
Question on the generative process of UIS-RNN

#20 123456789077 closed 5 years ago
3
Add a `partial_fit()` API

#19 wq2012 opened 5 years ago
0
handle overlapped speech

#18 PES2g closed 5 years ago
3
Publish the library as a package on PyPI

#17 wq2012 closed 5 years ago
0
Allow controlling verbosity level

#16 wq2012 closed 5 years ago
1
How can i train my own data on this ?

#15 NightFury10497 closed 5 years ago
1
run_test.sh problem

#14 77281900000 closed 5 years ago
11
Model predicts new cluster for each input after calling load()

#13 dalonlobo closed 5 years ago
15
Interpreting the loss values

#12 dalonlobo closed 5 years ago
1
2 space indentation

#11 dalonlobo closed 5 years ago
1
Question on training loss

#10 77281900000 closed 5 years ago
2
How to embedding audio stream data to k-vector (512)

#9 buaapengbo closed 6 years ago
1
Large datasets cause training machine to run out of memory

#8 xinli94 closed 5 years ago
4
Refactor fit() and predict()

#7 wq2012 closed 5 years ago
2
ValueError: not enough values to unpack (expected 2, got 1)

#6 MuruganR96 closed 6 years ago
5
Support half-life for learning rate

#5 wq2012 closed 6 years ago
0
Add support for estimation of crp_alpha

#4 wq2012 opened 6 years ago
5
Use a real sequence accuracy evaluation instead of an approximate accuracy

#3 wq2012 closed 6 years ago
0
Pretrained Models

#2 dsleo closed 6 years ago
1
Information about the Data

#1 dsleo closed 6 years ago
3