-
Hello, is anyone try this approach? This seems the fastest combination at this moment.
I've tried but it seems there is something wrong with my implementation, which generated inaudible audio (I can …
-
I have my own dataset
and my function added
```
def preprocess_aishell(datasets_root…
LmYjQ updated
5 years ago
-
I'm not sure if I'm doing something wrong, but I can't figure out how to run onsets_frames_transcription_transcribe. Any help would be very much appreciated!
I've tried `pip install magenta` and t…
-
Calling `librosa.load('101729.wav', sr=None)` ([download file here](https://drive.google.com/open?id=0B39u742eEiEqeno5cUlsUjIyUkE)) gives the following error:
```python
-----------------------------…
-
! Run is removed from /root/Trainings/ljspeech-stft_params-April-07-2020_10+27AM-fab74dd
Traceback (most recent call last):
File "train.py", line 724, in
main(args)
File "train.py", line 641, in m…
-
Tacotron2: https://arxiv.org/pdf/1712.05884.pdf
WaveRNN: https://github.com/erogol/WaveRNN forked from https://github.com/fatchord/WaveRNN
The idea is to add Tacotron2 as another alternative if i…
-
## 🐛 Bug
File
```
File "tmp.py", line 5, in
mfcc(x).shape
File "/mnt/lustre/sjtu/home/xg000/.conda/envs/torch10/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in…
-
I am looking to use and expand some transforms for audio. However, what is the recommended way of working with audeering/audtorch [audtorch](https://github.com/audeering/audtorch), [torchaudio](https…
-
Hi
I have run your model code in utils/model.py and saw that the output ahpe of line 67(melspectrogram) is (?,64,?,1) its confusing,because generally mel spectrograms are for examples 96* 64 ,they a…
-
## 🐛 Bug
`MelScale` and thus `MelSpectrogram` will not use the correct filterbank when `f_max` is not equal to `sample_rate // 2`.
## To Reproduce
Steps to reproduce the behavior:
The foll…