|
Speech Separation model do not use Multiple GPU. Only the first GPU is assigned
|
|
1
|
92
|
January 22, 2022
|
|
Complicated dataio pipeline
|
|
0
|
82
|
January 11, 2022
|
|
Realtime Speech Enhancement on Jetson Nano
|
|
0
|
108
|
January 11, 2022
|
|
Error in Training speech recognizer
|
|
1
|
81
|
January 11, 2022
|
|
Should LM is updated every change of corpus file?
|
|
2
|
128
|
January 11, 2022
|
|
Missing initial transcription in RNN-T
|
|
2
|
152
|
December 19, 2021
|
|
Align wav2vec2 latent representation and CTC predicted token
|
|
0
|
118
|
December 17, 2021
|
|
Another way of batch sampling
|
|
2
|
123
|
December 16, 2021
|
|
Does speech brain allow vocal recognition of phonemes?
|
|
6
|
906
|
December 15, 2021
|
|
Filterbank non-constant amplitudes
|
|
5
|
173
|
December 15, 2021
|
|
Fbank and MFCC modules compute an extra frame
|
|
3
|
129
|
December 13, 2021
|
|
Error while training the audio data with common voice
|
|
2
|
130
|
December 13, 2021
|
|
Microphone array have a wrong position in SB tutorial
|
|
1
|
148
|
December 12, 2021
|
|
DNS enhance spectral map recipe question
|
|
2
|
100
|
December 12, 2021
|
|
Feature request. Iteration number in training loop.
|
|
2
|
97
|
December 12, 2021
|
|
Diarization problem
|
|
1
|
143
|
December 12, 2021
|
|
OSError: libcudart.so.10.2: cannot open shared object file: No such file or directory
|
|
1
|
221
|
December 12, 2021
|
|
Finetuning SepFormer : CUDA out of Memory Error
|
|
3
|
251
|
November 29, 2021
|
|
How to get the model's gradient and wav's gradient?
|
|
2
|
108
|
November 8, 2021
|
|
Exporting to C++
|
|
1
|
148
|
November 5, 2021
|
|
Checkpointer Load Warning
|
|
1
|
123
|
November 5, 2021
|
|
Evaluate doesn't return the avg loss
|
|
2
|
108
|
November 4, 2021
|
|
Is Speechbrain Pytorch 1.10 compatible?
|
|
4
|
183
|
November 1, 2021
|
|
FORMAT OF DATA SET FOR MAKING CUSTOM LANGUAGE ASR SYSTEM (Speech Emotion and Speech to Text)
|
|
6
|
243
|
October 30, 2021
|
|
Speech enhancement model inference
|
|
9
|
601
|
October 29, 2021
|
|
Problem about Speaker Verification test batch size
|
|
4
|
210
|
October 29, 2021
|
|
Pretrained ECAPA-TDNN net outputs same feature vector for different signals
|
|
0
|
158
|
October 29, 2021
|
|
Use pretrained SpeechBrain model as Loss
|
|
9
|
187
|
October 29, 2021
|
|
DNN Beamforming and other front-ends modules
|
|
17
|
565
|
October 28, 2021
|
|
RNN-T joint network significantly consuming memory and causing OOM
|
|
3
|
149
|
October 27, 2021
|