b1935c97fa1175908c579a4db06214174253f5f4,server/synthesizer.py,Synthesizer,tts,#Synthesizer#Any#Any#,173

Before Change

                postnet_output, decoder_output, alignments, stop_tokens)

            if self.pwgan:
                vocoder_input = torch.FloatTensor(postnet_output.T).unsqueeze(0)
                if self.use_cuda:
                    vocoder_input.cuda()
                wav = self.pwgan.inference(vocoder_input, hop_size=self.ap.hop_length)
            elif self.wavernn:
                vocoder_input = None
                if self.tts_config.model == "Tacotron":
                    vocoder_input = torch.FloatTensor(self.ap.out_linear_to_mel(linear_spec=postnet_output.T).T).T.unsqueeze(0)

After Change

                vocoder_input = postnet_output[0].transpose(0, 1).unsqueeze(0)
                wav = self.vocoder_model.inference(vocoder_input)
                if self.use_cuda:
                    wav = wav.cpu().numpy()
                else:
                    wav = wav.numpy()
                wav = wav.flatten()
            elif self.wavernn:
                vocoder_input = None
                if self.tts_config.model == "Tacotron":
                    vocoder_input = torch.FloatTensor(self.ap.out_linear_to_mel(linear_spec=postnet_output.T).T).T.unsqueeze(0)

Instances