|
About the audio category
|
|
2
|
992
|
July 17, 2020
|
|
How to use and finetune XLS-R wave2vec2 feature extractor in PyTorch?
|
|
1
|
43
|
June 25, 2022
|
|
CNN ASR getting nan and core dump after epoch 1 with custom dataset
|
|
2
|
33
|
June 20, 2022
|
|
WavNet Synthesis
|
|
0
|
31
|
June 20, 2022
|
|
BERT style pretraining on spectrograms
|
|
7
|
110
|
June 2, 2022
|
|
Error importing Torchaudio
|
|
0
|
96
|
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
|
118
|
May 23, 2022
|
|
Pre-trained Model on Spectrograms
|
|
1
|
109
|
May 16, 2022
|
|
PyTorch equivalent of tf.gather
|
|
7
|
638
|
May 14, 2022
|
|
Raspberry pi 4 64-bit
|
|
1
|
124
|
May 14, 2022
|
|
Torchaudio.functional.lfilter VS scipy.signal.lfilter
|
|
3
|
134
|
May 11, 2022
|
|
Pretrain Resnet34 based on mel spectrogram features
|
|
0
|
58
|
May 5, 2022
|
|
Implementing scriptable channel masking transform for multi-channel input
|
|
0
|
71
|
April 29, 2022
|
|
How to feed mfcc features into Resnet/VGG
|
|
2
|
120
|
April 28, 2022
|
|
CTC loss error after first epoch
|
|
1
|
79
|
April 21, 2022
|
|
Unable to reproduce results in Emformer
|
|
8
|
158
|
April 20, 2022
|
|
RNN on a Spectrogram - Loss Isn't Going Down
|
|
4
|
116
|
April 19, 2022
|
|
[Lot of people have this issue] Porotype still does not load after installing the nightly build
|
|
5
|
140
|
April 8, 2022
|
|
Torchaudio.load is not able to find the backend soundfile
|
|
2
|
244
|
April 7, 2022
|
|
Adapting wav2vec2 to stream of int16
|
|
0
|
96
|
April 7, 2022
|
|
Numpy is not available error
|
|
3
|
1132
|
April 5, 2022
|
|
Ways to online inference streaming ASR
|
|
2
|
128
|
April 2, 2022
|
|
wav2vec for pre-training to extract high-dimensional speech features from datasets
|
|
12
|
308
|
March 31, 2022
|
|
Partially initialized module 'torchaudio' has no attribute 'pipelines'
|
|
2
|
211
|
March 31, 2022
|
|
Torchaudio VAD reverse effect
|
|
1
|
186
|
March 30, 2022
|
|
HuBERT to extract audio features
|
|
0
|
111
|
March 30, 2022
|
|
Failed to build Pytorch audio from source
|
|
4
|
337
|
March 12, 2022
|
|
Difficulty shaping 3 dimension tensors from MFCC transform for input into model
|
|
1
|
158
|
March 11, 2022
|
|
Error while obtaining an Inverse Spectrogram
|
|
1
|
195
|
March 11, 2022
|
|
Installing torchaudio on google colab
|
|
17
|
4626
|
March 8, 2022
|