Giters
janvainer
/
speedyspeech
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
248
Watchers:
10
Issues:
42
Forks:
36
janvainer/speedyspeech Issues
ZeroDivisionError when extracting duration
Closed
4 years ago
Comments count
2
Speedyspeech loss
Closed
4 years ago
Comments count
4
error in train
Updated
a year ago
if sample_rate is 16k, the reference hyperparamerter hop_size, win_size ..... how to set
Updated
a year ago
Comments count
1
create_dataset
Updated
a year ago
dataset
Updated
a year ago
create_dataset
Updated
a year ago
Unclear inference result
Closed
4 years ago
Comments count
10
question about the SSIM loss
Updated
2 years ago
chain of exponentials
Closed
2 years ago
Comments count
1
Positional encoding
Closed
3 years ago
Comments count
3
Residual shape in documentation
Updated
3 years ago
Comments count
2
RuntimeError: stack expects a non-empty TensorList
Updated
3 years ago
Comments count
10
pip install -r requirements.txt ERROR
Updated
3 years ago
Comments count
1
does speedyspeech support transfer learning?
Closed
3 years ago
Comments count
2
optimizations
Updated
3 years ago
how much time to train it?
Closed
3 years ago
Comments count
1
Why is there no dropout in the code?
Closed
3 years ago
Comments count
2
duration loss calculated in log domain or linear domain
Closed
3 years ago
Comments count
7
Duplicated padding when calculating STFT transformation.
Updated
3 years ago
Comments count
3
A mistake in positional encoding
Closed
3 years ago
Comments count
6
Extract durations from the trained model
Closed
3 years ago
Comments count
10
Time for training teacher model is quite slow.
Updated
3 years ago
Comments count
5
wav file quality - melgan vs griffinlim
Updated
3 years ago
Comments count
2
clarification request - normalization used in teacher model vs student
Closed
3 years ago
Comments count
4
Slow performance on aarch64 + GPU compared to x86 CPU
Closed
3 years ago
Comments count
5
Unstable audio generation towards the end of longer sentences using interference.py
Closed
3 years ago
Comments count
3
Is it possible to use other vocoders?
Closed
3 years ago
Comments count
7
Issues for multi_speedyspeech?
Closed
3 years ago
Comments count
5
trimming silences in the beginning and end of the audio
Closed
3 years ago
Comments count
2
Should the teacher model predict next frame?
Closed
4 years ago
Comments count
2
Add demo inference server
Closed
4 years ago
better than Tacotron2?
Closed
4 years ago
Comments count
2
the choice of positional encoding
Closed
4 years ago
Comments count
6
running error
Closed
4 years ago
Comments count
1
About SSIM loss
Closed
4 years ago
Comments count
2
I have support for other language?
Closed
4 years ago
Comments count
2
How to traini MelGAN
Closed
4 years ago
Comments count
4
RuntimeError: stack expects a non-empty TensorList
Closed
4 years ago
Comments count
5
mismatch commits between master code and released speedyspeech.pth
Closed
4 years ago
Comments count
4
how to remove redundant silence in the synthesized wav
Closed
4 years ago
Comments count
3
Why full connected layer replaced with conv1d?
Closed
4 years ago
Comments count
2