|
About the audio category
|
|
2
|
1075
|
July 17, 2020
|
|
Torch.stft and torch.istft with window function
|
|
3
|
44
|
September 23, 2022
|
|
Changing kernel size in wav2vec pretrained model
|
|
3
|
43
|
September 22, 2022
|
|
Back-propagate through torch.stft and torch.istft
|
|
4
|
45
|
September 20, 2022
|
|
Error importing Torchaudio
|
|
2
|
451
|
September 18, 2022
|
|
How to apply CNN to live/variable-length audio?
|
|
0
|
46
|
September 11, 2022
|
|
Torchaudio backend change on Windows
|
|
0
|
56
|
September 5, 2022
|
|
CNN speech recognition model good train/test accuracy yet poor inference on outside data?
|
|
3
|
78
|
September 4, 2022
|
|
CTCDecoder on GPU
|
|
1
|
57
|
September 1, 2022
|
|
How can I classify the language of voice data?
|
|
0
|
51
|
August 30, 2022
|
|
How can I classify words spoken by one person?
|
|
1
|
77
|
August 24, 2022
|
|
Exploding loss in encoder/decoder model
|
|
1
|
91
|
August 23, 2022
|
|
Audio frame wise training
|
|
0
|
77
|
August 3, 2022
|
|
Can I use TimeStretch on Mel-frequency spectrograms?
|
|
0
|
79
|
August 2, 2022
|
|
How to format forward function for multiple inputs
|
|
5
|
103
|
August 2, 2022
|
|
Converting architecture to multiple input, single output
|
|
0
|
95
|
July 31, 2022
|
|
Using nn.transformer for audio spectrograms?(speech recognition)
|
|
0
|
71
|
July 27, 2022
|
|
How to use torchauido load mp3 file
|
|
0
|
79
|
July 19, 2022
|
|
MFCC and LFCC in frame by frame processing
|
|
1
|
163
|
July 13, 2022
|
|
Numpy is not available error
|
|
7
|
3336
|
July 11, 2022
|
|
Random paramters value for torchaudio augmentation
|
|
1
|
92
|
July 1, 2022
|
|
How to use and finetune XLS-R wave2vec2 feature extractor in PyTorch?
|
|
1
|
136
|
June 25, 2022
|
|
CNN ASR getting nan and core dump after epoch 1 with custom dataset
|
|
2
|
104
|
June 20, 2022
|
|
WavNet Synthesis
|
|
0
|
154
|
June 20, 2022
|
|
BERT style pretraining on spectrograms
|
|
7
|
215
|
June 2, 2022
|
|
Wav2Vec2: ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length
|
|
0
|
405
|
May 23, 2022
|
|
Pre-trained Model on Spectrograms
|
|
1
|
226
|
May 16, 2022
|
|
PyTorch equivalent of tf.gather
|
|
7
|
866
|
May 14, 2022
|
|
Raspberry pi 4 64-bit
|
|
1
|
242
|
May 14, 2022
|
|
Torchaudio.functional.lfilter VS scipy.signal.lfilter
|
|
3
|
430
|
May 11, 2022
|