Fix #2745

[erogol]

No description provided.

[tazz4843]

CLI command referenced in #2745 throws this error

Traceback (most recent call last):
  File "/home/zero/PycharmProjects/scripty-tts-server/venv/bin/tts", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/home/zero/PycharmProjects/scripty-tts-server/venv/lib/python3.11/site-packages/TTS/bin/synthesize.py", line 447, in main
    wav = synthesizer.tts(args.text, speaker_name=args.speaker_idx)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/zero/PycharmProjects/scripty-tts-server/venv/lib/python3.11/site-packages/TTS/utils/synthesizer.py", line 365, in tts
    outputs = self.tts_model.synthesize(
              ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/zero/PycharmProjects/scripty-tts-server/venv/lib/python3.11/site-packages/TTS/tts/models/tortoise.py", line 522, in synthesize
    outputs = self.inference_with_config(
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/zero/PycharmProjects/scripty-tts-server/venv/lib/python3.11/site-packages/TTS/tts/models/tortoise.py", line 592, in inference_with_config
    return self.inference(text, **settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/zero/PycharmProjects/scripty-tts-server/venv/lib/python3.11/site-packages/TTS/tts/models/tortoise.py", line 680, in inference
    ) = self.get_conditioning_latents(
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/zero/PycharmProjects/scripty-tts-server/venv/lib/python3.11/site-packages/TTS/tts/models/tortoise.py", line 434, in get_conditioning_latents
    auto_conds = torch.stack(auto_conds, dim=1)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: stack expects a non-empty TensorList

if the directory doesn't have a .wav file, fixing this for UX might be a good idea.

[erogol]

@tazz4843 Can't reproduce this. How many audio files do you have for the speaker?