-
I mean pre processing the mels.
https://github.com/jik876/hifi-gan/issues/61
-
Hi @p0p4k, thanks for making this repo!
I am currently trying to train a 44.1kHz English model, but my model is struggling with a rather high duration loss when compared against your TensorBoard lo…
w11wo updated
3 months ago
-
Hello, could you please tell me why does the network ask to enter any spectrogram at the time of the outputting the result?
I mean this command
```python inference.py -p [checkpoint path] -i [inpu…
-
The shape of mel output of Tacotron2 is bigger than mel extracted from audio and the model has issue
```
File "train.py", line 113, in train
for i, batch in enumerate(train_loader):
File "/…
-
I use this shape of Mel to train the hifi gan, it has no any error when training. however, when I use the model to inference from tacotron file ,is reminds me it must be 80 channels
![图像2023-2-26 0…
-
Hi,
I am training the V1 version of HiFi-GAN. I downsampled wavs to 16kHz and used a hopsize of 200 frames to make Mel-spectrums. Accordingly, I configed the upsampling scales as [5, 5, 4, 2].
A…
-
Hi, thanks for your nice jobs. I used your codes for ny own datasets and the synthesized voices seems not that normal at 160K steps now. Though we could still figure out what's being saied, the spect…
-
(env) (base) C:\Users\prost\Wav2Lip>python inference.py --checkpoint_path checkpoints/wav2lip_gan.pth --face joseph.mp4 --audio josephvoice.mp3
Using cpu for inference.
Reading video frames...
Numb…
-
/home/rian0532/anaconda3/envs/py39Ubuntu/lib/python3.9/site-packages/torch/nn/modules/conv.py:306: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/sr…
-
Hello Mustafa & Ziad,
I have checked your awesome work, which is really helpful to me, but I have a question please ,,I am new to this field, so could you please share with me a good reference to u…