-
Traceback (most recent call last):
File "/workdir/waveglow/inference.py", line 75, in
args.output_dir, args.sampling_rate, args.is_fp16)
File "/workdir/waveglow/inference.py", line 35, in …
-
I made the modifications suggested in https://github.com/NVIDIA/waveglow/issues/106 because I want to test the model in my laptop for inference before getting to fine-tune a model and I now get this e…
-
Hi,
Thank you for your nice job. But I found that either your FloWaveNet or NVIDIA's WaveGlow has a problem of containing periodic noise.
**
*PyTorch/Tacotron2/WaveGlow*
**Describe the bug**
Hi. I tried to train the WaveGlow model and encountered `Loss is NaN` problem after 80 epoches. Before epoch 8…
-
I am using tacotron-cli and waveglow-cli on Google Colab, and am experiencing slow mel inference with waveglow-cli. The following is the code I am executing and the resulting log with the inference du…
-
I made jupyter notebook for WaveGlow Model in Google COLAB. Within 10 minutes including time to get weight file(2GB) , you could synthesize voice.
https://github.com/yhgon/waveglow/blob/master/infere…
yhgon updated
5 years ago
-
## 一言でいうと
Glow+WaveNetの手法により高速な音声生成を行う手法。ネットワークを可逆変換にする(Glow)ことで、ノイズ=>音声の尤度と音声=>ノイズの尤度を等価にし、計算しやすい後者から前者を計算する。(可逆な)アフィン変換的な処理を行うが、このシフト量をWaveNet on メルケプストラムで計算する。
 and it works kinda good except it skipping some random word in the sentence; rarely happened but its not good at all; and it al…
-
Do you have a paper discribed this implementation. I would like to see the comparision with others model and baseline (tacotron2 + waveglow)