issues
search
mravanelli
/
pytorch-kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
2.36k
stars
446
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
res.res
#259
LYPinASR
opened
1 year ago
0
Add support for GAN front-end training and evaluation
#258
walterheymans
closed
2 years ago
0
using different features instead of FMLLR
#257
Miamoto
opened
2 years ago
0
err_te is 1
#256
severusbunny
opened
3 years ago
0
Use final_architecture1.pkl for live test
#255
spacecd
closed
3 years ago
4
Before switch to SpeechBrain, how to use trained model in pytorch
#254
sun-peach
opened
3 years ago
0
Unable to run forwarding step on test set
#253
kevinmchu
opened
3 years ago
0
x-vector DNN model
#252
jvel07
opened
3 years ago
0
How to train/decode on reverberant speech?
#251
kevinmchu
opened
3 years ago
1
No Decoding Output
#250
kevinmchu
closed
3 years ago
20
Word transcription of TIMIT dataset
#249
shessam
opened
3 years ago
1
Does pytorch-kaldi support chain model training?
#248
Vanka0051
opened
3 years ago
1
No WER stdout when decoding
#247
hellboywyh
opened
3 years ago
0
KaldiFatalError during decoding phase
#246
tanzyy96
opened
4 years ago
0
Support for torch.nn.Transformer Class?
#245
niticon
opened
4 years ago
1
The loss curve of train and dev is reasonable but why the Test Error keeps 53% or so?
#244
hellboywyh
closed
3 years ago
8
Question about the Dimension of wx.0.weight in my mlp model
#243
zyn2609530
opened
4 years ago
1
input shape of nns
#242
HaoranWeiUTD
opened
4 years ago
3
Can we resume training from the epoch we got interruption
#241
sun-peach
opened
4 years ago
4
Do bidirectional layers share the input-to-hidden weights?
#240
timolohrenz
closed
4 years ago
2
How to setup parameters in "cfg/TIMIT_baselines/TIMIT_liGRU_fmllr.cfg"?
#239
ReinholdM
opened
4 years ago
1
How to setup parameters in "cfg/TIMIT_baselines/TIMIT_liGRU_fmllr.cfg"?
#238
ReinholdM
closed
4 years ago
6
Training on multi-gpu very slow
#237
sun-peach
opened
4 years ago
4
How can I load a trained model in python with torch?
#236
sun-peach
opened
4 years ago
2
bad forward .ark file output when out model is a sequential model
#235
timolohrenz
opened
4 years ago
0
ValueError: all the input array dimensions for the concatenation axis must match exactly, but along dimension 0, the array at index 0 has size 5658 and the array at index 1 has size 5640
#234
aziryasin
opened
4 years ago
2
Chunk Mean and Variance Normalization
#233
timolohrenz
closed
4 years ago
3
Librispeech: Adding lattice rescoring
#232
omprakashsonie
closed
4 years ago
12
fix bug when feats.scp changes name
#231
Baileyswu
opened
4 years ago
0
Fix issue #157 - training crashes when CPU is used
#230
Serhiy-Shekhovtsov
closed
4 years ago
1
Update neural_networks.py
#229
sungyihsun
closed
4 years ago
0
Production mode save_outputs: getting bad .ark files
#228
matthewkperez
closed
4 years ago
1
Fix typo in README.md.
#227
tzyll
closed
4 years ago
0
Adding FusionRNN + QLSTM cfg + small QLSTM change
#226
TParcollet
closed
4 years ago
0
add quaternion proto (QLSTM) and quaternion_neural_networks.py
#225
xinchiqiu
closed
4 years ago
1
The parameter update of sincconv
#224
piplyman
closed
4 years ago
1
Loss not decreasing for Hybrid CNN+DNN and CNN+BLSTM models.
#223
bipashasen
closed
4 years ago
1
Support more models of kaldi like chain model
#222
a550461053
closed
4 years ago
2
Silence detection (VAD)
#221
matthewkperez
closed
4 years ago
1
Error with getting shared_list
#220
seas2nada
closed
4 years ago
0
Does mini batch order matter?
#219
matthewkperez
closed
4 years ago
4
Error in the decoding
#218
mnabihali
closed
4 years ago
11
ERROR: hmm-info command doesn't exist. However I have `hmm-info` working in terminal.
#217
andi611
closed
4 years ago
1
Cannot reproduce LSTM result on TIMIT
#216
arvoelke
closed
4 years ago
7
ValueError: Precision not allowed in integer format specifier
#215
mnabihali
closed
4 years ago
13
Is there a problem with bidirectional LSTM?
#214
lezasantaizi
closed
4 years ago
1
How could I get the complete decoding result instead of PARTIAL result when decoding.
#213
xixihahaggg
closed
4 years ago
1
Problem with loading rawwav as feature, it costs too much time
#212
liuzz13
closed
4 years ago
2
Cannot get WER when running TIMIT_SincNet_raw experiment
#211
zehaitu
closed
4 years ago
2
Online speech recognition
#210
victornoriega
closed
4 years ago
5
Next