Айдос Сарсембаев

Hi! Is it normal to train a multi-speaker model where two speakers speak one language (i.g. Kazakh), and the third one speaks a different (i.g. Russian) ? Is there anything...

Is there any way to train a model that can make an inference with controlled stress on vowels? For instance: aidOs has a stress on "O" sound. Aidos has a...

Hi! in `model.module` line 128, we have ``` if duration_target is not None: x, mel_len = self.length_regulator(x, duration_target, max_len) duration_rounded = duration_target else: duration_rounded = torch.clamp( (torch.round(torch.exp(log_duration_prediction) - 1) *...