diff --git a/src/python_run/piper/voice.py b/src/python_run/piper/voice.py index 9fb2906..0360c27 100644 --- a/src/python_run/piper/voice.py +++ b/src/python_run/piper/voice.py @@ -162,25 +162,24 @@ class PiperVoice: dtype=np.float32, ) + args = { + "input": phoneme_ids_array, + "input_lengths": phoneme_ids_lengths, + "scales": scales + } + + if self.config.num_speakers <= 1: + speaker_id = None + if (self.config.num_speakers > 1) and (speaker_id is None): # Default speaker speaker_id = 0 - sid = None - if speaker_id is not None: sid = np.array([speaker_id], dtype=np.int64) + args["sid"] = sid # Synthesize through Onnx - audio = self.session.run( - None, - { - "input": phoneme_ids_array, - "input_lengths": phoneme_ids_lengths, - "scales": scales, - "sid": sid, - }, - )[0].squeeze((0, 1)) + audio = self.session.run(None, args, )[0].squeeze((0, 1)) audio = audio_float_to_int16(audio.squeeze()) - return audio.tobytes()