Fix voice conversion inference

TTS/bin/synthesize.py

@@ -171,7 +171,7 @@ def main():
         help="wav file(s) to condition a multi-speaker TTS model with a Speaker Encoder. You can give multiple file paths. The d_vectors is computed as their average.",
         default=None,
     )
-    parser.add_argument("--gst_style", help="Wav path file for GST stylereference.", default=None)
+    parser.add_argument("--gst_style", help="Wav path file for GST style reference.", default=None)
     parser.add_argument(
         "--list_speaker_idxs",
         help="List available speaker ids for the defined multi-speaker model.",

TTS/tts/models/vits.py

@@ -1127,7 +1127,7 @@ def inference_voice_conversion(
             self.config.audio.hop_length,
             self.config.audio.win_length,
             center=False,
-        ).transpose(1, 2)
+        )
         y_lengths = torch.tensor([y.size(-1)]).to(y.device)
         speaker_cond_src = reference_speaker_id if reference_speaker_id is not None else reference_d_vector
         speaker_cond_tgt = speaker_id if speaker_id is not None else d_vector
@@ -1157,7 +1157,7 @@ def voice_conversion(self, y, y_lengths, speaker_cond_src, speaker_cond_tgt):
         else:
             raise RuntimeError(" [!] Voice conversion is only supported on multi-speaker models.")
 
-        z, _, _, y_mask = self.posterior_encoder(y.transpose(1, 2), y_lengths, g=g_src)
+        z, _, _, y_mask = self.posterior_encoder(y, y_lengths, g=g_src)
         z_p = self.flow(z, y_mask, g=g_src)
         z_hat = self.flow(z_p, y_mask, g=g_tgt, reverse=True)
         o_hat = self.waveform_decoder(z_hat * y_mask, g=g_tgt)

TTS/utils/synthesizer.py

@@ -315,7 +315,7 @@ def tts(
             # get the speaker embedding or speaker id for the reference wav file
             reference_speaker_embedding = None
             reference_speaker_id = None
-            if self.tts_speakers_file or hasattr(self.tts_model.speaker_manager, "speaker_ids"):
+            if self.tts_speakers_file or hasattr(self.tts_model.speaker_manager, "ids"):
                 if reference_speaker_name and isinstance(reference_speaker_name, str):
                     if self.tts_config.use_d_vector_file:
                         # get the speaker embedding from the saved d_vectors.