Thi Vũ

why do we need multiple languages & multiple speakers?

2

hi there, thank you for the interesting work! i want to train a model to perform code-switching TTS / voice conversion for only 2 languages: Vietnamese and English. i assume...

Checkpoint request

1

The Google Drive links for the checkpoints are now not publicly available anymore. Is it a mistake? Can you kindly make it available again? Thank you a lot for the...

where are the discrete units weights from?

1

in the train.py file, you have an argument named `--warmstart` to allow "initialize[ing] from the fairseq HuBERT checkpoint". I wonder which checkpoint is it since fairseq offers a lot of...

hi, thank you for sharing your code. i am trying to do voice conversion from English speech to Vietnamese speaker. to do that, i did the following steps - extract...

[Bug] YourTTS alignment is weird

1

### Describe the bug I am training YourTTS model on VCTK using the recipe provided in this repo. But the alignment seems off, and the audio output is not great,...

Problem downloading dataset

1

i want to try out this model but could not find the Nsynth dataset anywhere. the link on the [official website](https://magenta.tensorflow.org/datasets/nsynth) seems to be broken. can anyone kindly share this...

about silence tokens during inference

1

i see that the default values for `silence_tokens` during inference are [1388,1898,131]. my questions: 1. why is there more than one silence token? 2. how do `silence_tokens` differ from the...