Voice Cloning Error

[stanleyshly]

I'm currently trying to do voice cloning with this command
/TTS/bin/synthesize.py --speaker_wav ./sample_recording.wav --text 'this is a test sentence' --model_name "tts_models/en/vctk/vits" --vocoder_name "vocoder_models/en/vctk/hifigan_v2"
However, I get this error:

Traceback (most recent call last):
  File "/Users/user/Desktop/TTS/./TTS/bin/synthesize.py", line 295, in <module>
    main()
  File "/Users/user/Desktop/TTS/./TTS/bin/synthesize.py", line 287, in main
    wav = synthesizer.tts(args.text, args.speaker_idx, args.language_idx, args.speaker_wav)
  File "/usr/local/lib/python3.9/site-packages/TTS/utils/synthesizer.py", line 245, in tts
    speaker_embedding = self.tts_model.speaker_manager.compute_d_vector_from_clip(speaker_wav)
  File "/usr/local/lib/python3.9/site-packages/TTS/tts/utils/speakers.py", line 287, in compute_d_vector_from_clip
    d_vector = _compute(wf)
  File "/usr/local/lib/python3.9/site-packages/TTS/tts/utils/speakers.py", line 270, in _compute
    waveform = self.speaker_encoder_ap.load_wav(wav_file, sr=self.speaker_encoder_ap.sample_rate)
AttributeError: 'NoneType' object has no attribute 'load_wav'

How do I fix this error, and why is it being caused.

[p0p4k]

speaker_encoder_ap <-- need to look at that. Find where it is initialised and print it out.

[TheMrZZ]

VITS cannot be used for zero-shot voice cloning. Yes, the error message is terribly unexplicit.

Similar issue is #1440