HarryVolek PyTorch_Speaker_Verification issues

HarryVolek / PyTorch_Speaker_Verification

PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.

BSD 3-Clause "New" or "Revised" License

578 stars 164 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Running train_ speech_ embedder.py reports an error during training

#79 ZZZzhoup opened 2 years ago
0
I have trained all data , but how to use it ?

#78 TonyB22 opened 2 years ago
0
Update data_preprocess.py

#77 idiomaticrefactoring opened 2 years ago
0
how can I reproduce the result: EER across 10 epochs: 0.0377 ?

#76 JiaqingFu opened 3 years ago
0
Single inference

#75 fabianoluzbr opened 3 years ago
0
Full sc

#74 JeffT13 closed 4 years ago
0
Shuffling wav files in dataloader does not ensure that all the training files are checked in each epoch

#73 dkatsiros opened 4 years ago
2
error in training

#72 Jason-1998 closed 4 years ago
2
Changing the sampling frequency

#71 neerajkuhike opened 4 years ago
0
The contrast loss

#70 amadeusuzx closed 4 years ago
1
new speaker

#69 ooobsidian opened 4 years ago
1
about config

#68 zyc1310517843 opened 4 years ago
1
How to train d-vector model for using on diarization with my own data?

#67 mesut92 opened 4 years ago
2
What is the duration of audio of each D vector embedding that is created?

#66 abhilashnayak opened 4 years ago
0
Change the code to use multi-gpu, but can not speed up the training.

#65 Naminwang opened 4 years ago
2
Determining time indexes for embeddings?

#64 chrisspen opened 5 years ago
2
Unable to run dvector_create.py, file does not start with RIFF id

#63 chrisspen opened 5 years ago
1
Unable to test

#62 chrisspen opened 5 years ago
0
Very slow training on CPU

#61 chrisspen opened 5 years ago
2
How to handle multiple speakers?

#60 chrisspen opened 5 years ago
0
Align embeddings

#59 pravn opened 5 years ago
0
# this works fine for timit but if you get array of shape 0 for any o…

#58 pranshurastogi29 closed 4 years ago
1
getting 0 shape array in save_spectrogram_tisv (vctk dataset )

#57 pranshurastogi29 closed 5 years ago
2
How to create train_sequence.npy, and train_cluster_ids.npy.

#56 Sadam1195 closed 5 years ago
12
Things to check when testing with different DB

#55 hash2430 opened 5 years ago
3
Possible bug report and suggestion on how to fix it.

#54 hash2430 opened 5 years ago
0
doubts on the config.yaml

#53 BarCodeReader closed 5 years ago
2
Speaker Verification Predict

#52 Kailegh opened 5 years ago
0
GE2E loss can work with cnn

#51 wrongbattery opened 5 years ago
0
No backend error (in librosa.core.load in preprocessing data)

#50 nidhal1231 closed 5 years ago
0
Calculating EER

#49 nidhal1231 opened 5 years ago
4
Frame rate problem

#48 nidhal1231 closed 5 years ago
1
lstm input wrong shape

#47 cavus700 closed 5 years ago
2
poor performance

#46 nidhal1231 closed 5 years ago
1
Overfitting

#45 biswasingh closed 5 years ago
1
train_speech_embedder.py:batch_id

#44 yahcong opened 5 years ago
2
error in data_preprocess.py (save_spectrogram_tisv() function)

#43 nidhal1231 closed 5 years ago
1
about the sampling rate

#42 nkcdy closed 5 years ago
1
align_embeddings()

#41 nidhal1231 closed 5 years ago
1
Embedder-net()

#40 nidhal1231 closed 5 years ago
1
Bitrate/Sample Rate Differences

#39 bitnom opened 5 years ago
1
Workflow of the project

#38 ahsanmemon closed 5 years ago
7
About Data_loader.py, "utterance = utterance[:, :, 160]", why we use the num 160?

#37 Bovey0809 closed 5 years ago
1
DataLoader

#36 nidhal1231 closed 5 years ago
0
Correctness of d-vectors

#35 nidhal1231 closed 5 years ago
0
How to use dvector_create.py

#34 zeyuanchen23 opened 5 years ago
7
Vectorized the util calculations

#33 seandickert closed 4 years ago
2
How to Use Your Audio Data Set

#32 zyc1310517843 opened 5 years ago
2
Two question on Embeddings

#31 mazzzystar closed 5 years ago
1
Fix the bug of Embedding norm and update the ERR

#30 mazzzystar closed 5 years ago
2