ivancarapinha

Dealing with words with multiple pronunciations

2

Hello, Since this g2p transformer performs phonetic transcription word by word, how does it select the correct pronunciation for a word that has several possible pronunciations? This is very common...

Multi-GPU training

3

Hello, Could you please specify the steps to enable multi-GPU training, please? I set `distributed_run=True` in `hparams.py` and then set `--n_gpus=2` and `CUDA_VISIBLE_DEVICES=0,3` in file `run.sh` to select GPUs 0...

Training the model for a different language

1

Hello @jxzhanggg, First of all, thank you for your helpful replies to the previous issues I posted. I would like to adapt this voice conversion model to European Portuguese. The...

Why the embedding layer instead of the one-hot audio vector?

1

Hello, In the original implementation of this model, the authors employed a one-hot audio vector of dimension 1024. Unfortunately, the authors did not detail much about this one-hot vector in...