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:

After Change

        // compute stats
        process_time = time.time() - start_time
        audio_time = len(wavs) / self.tts_config.audio["sample_rate"]
        print(f" > Processing time: {process_time}")
        print(f" > Real-time factor: {process_time / audio_time}")
        return out

Instances