-
Hey, I was wondering what sort of changes it would take to the training script to be able to train HiFiGAN on higher quality data like [LibriTTS ](https://www.openslr.org/60/)or [LibriTTS-R](https://w…
-
Hey Mick going back a few years to you mentioned in the oF forum and in you paper on Maximilian released in 2010 in the future work section that you were aiming to make a phase vocoder example with M…
-
### 🐛 Describe the bug
I am trying to reconstruct a waveform by composing the `InverseMelScale` transform and the `GriffinLim` transform. The operation hangs while running `InverseMelScale`. I switch…
-
Hi, I trained duration extractor and speedyspeech with my own dataset which is korean single speech dataset
(RIFF (little-endian) data, WAVE audio, Microsoft PCM, 16 bit, mono 22050 Hz)
I just chang…
-
Hello how are you?
I'm curious to know how to use torchsubband in practice,
I would like to know if it is already integrated in MSS-Challenge-CWS-PResUNet and I would like to know if it would al…
-
Hello,
I am working on a project aimed at generating drum loops conditioning only on global class labels (without neural vocoding on mel-spectrograms). I modified the diffwave model of this repositor…
-
Good morning, I run through all training process with my own dataset, I run the predict with HiFiGAN vocoder with this setting :
- parser.add_argument('--voc', dest='vocoder', default='hifigan')
…
-
Hi, Nemo Developer:
Happy new year first.
**Describe the bug**
I am trying to have a trial on voice clone. So I am trying to finetune a TTS model based on a test person's voice clips. Have s…
-
Hi
I am curious if we increase the number of layers for the duration, pitch, and energy using the 'duration_predictor_layers' parameter and some other parameters in the architecture, will it improve…
-
Many of our functions use padding to simplify vectorization of certain operations, eg:
https://github.com/librosa/librosa/blob/aec87d801144168d95142386a3efd200cb3dde76/librosa/util/utils.py#L943-L9…