Issues
- 8
TypeError: ('Unrecognized rnn type: ', 'qrnn')
#93 opened by delip - 0
facing issue while importing library
#129 opened by palashmoon - 2
Unable to install the requirnment.txt
#128 opened by palashmoon - 3
No module named 'ahoproc_tools'
#3 opened by almondUser3 - 0
- 4
- 2
load pretrained worker weights
#88 opened by MittalShruti - 1
Reproduce the supervised training with TIMIT ASR
#89 opened by Fuann - 24
self-supervised training from scratch
#90 opened by MittalShruti - 5
Audio buffer and Padding size problems
#91 opened by teinhonglo - 2
Question about distortion file
#97 opened by RE-N-Y - 2
ASR experiment with custom dataset
#107 opened by zmf0507 - 1
Reproduce Self-Supervised Training on LibriSpeech
#108 opened by Charlie0215 - 0
About Making the Dataset Configuration File
#126 opened by uuwz - 0
Issue in installation
#122 opened by tarun360 - 0
Question about the testing dataset
#121 opened by Fuann - 0
- 0
Question about SimpleAdditive transform
#119 opened by toco2270853 - 2
Training from scracth
#113 opened by kame5 - 1
- 0
Unable to load models
#118 opened by happypanda5 - 0
Question about make_trainset_statistics.py
#116 opened by Imenbaa - 3
Training pase+:RuntimeError: Legacy autograd function with non-static forward method is deprecated.
#114 opened by Imenbaa - 1
Train and valid losses
#96 opened by MittalShruti - 0
Load pretrrained SincNet
#117 opened by pollytur - 1
ERROR: Failed building wheel for pycodec2
#104 opened by deepesh321 - 1
No module name 'pycodec2'
#87 opened by MittalShruti - 0
- 0
Regarding speaker recognition in PASE
#112 opened by Some-random - 0
Invalid floating-point option Error
#111 opened by tanzyy96 - 0
LibriSpeechSegTupleWavDataset neighbor has bug?
#110 opened by ArtemisZGL - 2
Running on multiple GPUs
#30 opened by emirdemirel - 0
Create chime5segment
#109 opened by DungNguyen83 - 0
Using PASE for speech emotion recognition
#6 opened by akashicMarga - 7
ASR experiment on TIMIT dataset
#82 opened by zengchang233 - 1
Argument #4: Padding size should be less than the corresponding input dimension, but got: padding (0, 10416) at dimension 2 of input [1, 1, 5584]
#95 opened by lianrzh - 0
- 0
Error while setting trans_cache in train.py
#92 opened by MittalShruti - 3
Trying to load the pretained model
#83 opened by MittalShruti - 1
input file to segment the dataset
#86 opened by MittalShruti - 1
Fine tune the pre-trained weights
#84 opened by MittalShruti - 8
.scp file for train/test set
#85 opened by MittalShruti - 2
- 6
- 0
- 2
Train an Emotion Detection Model
#7 opened by kaustumbh7