Closed Pydataman closed 2 months ago
This part of the parameters is used to predict the speaker id during the training process and is not used during inference. Please ignore it.
This part of the parameters is used to predict the speaker id during the training process and is not used during inference. Please ignore it.
@HeCheng0625 that means there were 245200 speakers during training?
Hi, we're closing this thread since the question about number of speakers in FACodec training is not directly related to this repo, for more detailed training we recommend looking at the latest FACodec reproduce in latest Amphion release (currently in pr). Thanks!
if self.use_gr_x_timbre: self.x_timbre_predictor = nn.Sequential( GradientReversal(alpha=1), CNNLSTM(in_channels, 245200, 1, global_pred=True), )
Why is there a parameter
245200
in the codes?