[Bug] mps doesn't seem to work

[ajkessel]

Describe the bug

Intel Mac.

tts=TTS(model_name='multi-dataset/xtts_v2/en',progress_bar=True).to('mps')
tts.tts_to_file(text='testing', file_path='out.wav', speaker='Craig Gutsy', language='en')

results in

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "./.venv/lib/python3.11/site-packages/TTS/api.py", line 334, in tts_to_file
    wav = self.tts(
          ^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/TTS/api.py", line 276, in tts
    wav = self.synthesizer.tts(
          ^^^^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/TTS/utils/synthesizer.py", line 386, in tts
    outputs = self.tts_model.synthesize(
              ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/TTS/tts/models/xtts.py", line 412, in synthesize
    return self.inference(text, language, gpt_cond_latent, speaker_embedding, **settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/TTS/tts/models/xtts.py", line 541, in inference
    gpt_codes = self.gpt.generate(
                ^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/TTS/tts/layers/xtts/gpt.py", line 590, in generate
    gen = self.gpt_inference.generate(
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/transformers/generation/utils.py", line 1829, in generate
    self._prepare_special_tokens(generation_config, kwargs_has_attention_mask, device=device)
  File "./.venv/lib/python3.11/site-packages/transformers/generation/utils.py", line 1678, in _prepare_special_tokens
    and isin_mps_friendly(elements=eos_token_tensor, test_elements=pad_token_tensor).any()
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "./.venv/lib/python3.11/site-packages/transformers/pytorch_utils.py", line 325, in isin_mps_friendly
    return elements.tile(test_elements.shape[0], 1).eq(test_elements.unsqueeze(1)).sum(dim=0).bool().squeeze()
                         ~~~~~~~~~~~~~~~~~~~^^^
IndexError: tuple index out of range

but if I change the to setting to cpu it works.

To Reproduce

Shown above

Expected behavior

No error

Logs

Shown above

Environment

- TTS 0.22.0
- numpy 1.26.4
- pytorch 2.2.2
- python 3.11.10
- Darwin Kernel Version 24.0.0: Mon Aug 12 20:54:30 PDT 2024; root:xnu-11215.1.10~2/RELEASE_X86_64"

Additional context

No response

[saiteja-yadav]

Show me a video....,

[ajkessel]

@saiteja-yadav I'm confused--you actually want a video showing this exception? Here it is, if you really want it.

Video_2024-09-29_225659.mp4