-
I am wondering how would I train this model using the generated GTA mels output from a Tacotron-2 model. Any advice? Thank you!
-
I found the tf version is slower than the torch version of hifigan during training. Is that normal?
`[train]: 0%| | 1901/2000000 [1:56:07
-
Error when I try to train vocoder with custom dataset.
```
> Using CUDA: True
> Number of GPUs: 1
fatal: not a git repository (or any of the parent directories): .git
> Git Hash: 0000000
>…
-
I used the `dev` branch training PWGAN, then i looked into the tensorboard results, it seems that the spectrograms look weird. May i ask whether i did something wrong or i miss something?
I used th…
-
I am converting the multiband-Mel gan model into Tf-light with this code.
config_file = "./multiband_melgan.v1.yaml"
model_path = "./mbMelgan_generator-2560000.h5"
with open(config_fi…
-
In general, I want to have teacher forcing pas and self-generated (free-running generative) pass aka professor forcing.
For now, looks like I need to merge FullAttention RecurrentFullAttention Recu…
-
Ich bin beim letzten Punkt angekommen:
`CUDA_VISIBLE_DEVICES="0" python TTS/mozilla_voice_tts/bin/train_vocoder.py --config_path vocoder_config.json
`
Ich erhalte allerdings die Fehlermeldung
…
-
Hi, as Eren requested, this is an issue to follow progress of the training a larger PWGAN model for multiple speakers.
-
I used the colab and it worked beautifully, THANKS!
I have a problem. Whenever the audio has a silence piece the original mouth movement remains unchanged.
I've tried with "mmm" to "shutup". But it …
-
Hi,
I'm looking to convert the [pretrained universal vocoder for Multi-band MelGAN ](https://github.com/TensorSpeech/TensorFlowTTS/tree/master/examples/multiband_melgan#pretrained-models-and-audio-…