aten::isin.Tensor_Tensor_out is not currently implemented for the MPS device

[Amandrs]

~ via 🐍 v3.11.9 (insanely-fast-whisper)
❯ pipx list
venvs are in ~/.local/pipx/venvs
apps are exposed on your $PATH at ~/.local/bin
manual pages are exposed at ~/.local/share/man
   package insanely-fast-whisper 0.0.15, installed using Python 3.11.9
    - insanely-fast-whisper
~ via 🐍 v3.11.9 (insanely-fast-whisper)
❯ ~/.local/bin/insanely-fast-whisper --file-name audio.wav --device-id mps
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
🤗 Transcribing... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0:00:29
Traceback (most recent call last):
  File "~/.local/bin/insanely-fast-whisper", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/insanely_fast_whisper/cli.py", line 159, in main
    outputs = pipe(
              ^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 285, in __call__
    return super().__call__(inputs, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/pipelines/base.py", line 1235, in __call__
    return next(
           ^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/pipelines/pt_utils.py", line 124, in __next__
    item = next(self.iterator)
           ^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/pipelines/pt_utils.py", line 269, in __next__
    processed = self.infer(next(self.iterator), **self.params)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/pipelines/base.py", line 1150, in forward
    model_outputs = self._forward(model_inputs, **forward_params)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 508, in _forward
    tokens = self.model.generate(
             ^^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/models/whisper/generation_whisper.py", line 578, in generate
    outputs = super().generate(
              ^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/generation/utils.py", line 1758, in generate
    result = self._sample(
             ^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/generation/utils.py", line 2410, in _sample
    next_token_scores = logits_processor(input_ids, next_token_logits)
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/generation/logits_process.py", line 98, in __call__
    scores = processor(input_ids, scores)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "~/.local/pipx/venvs/insanely-fast-whisper/lib/python3.11/site-packages/transformers/generation/logits_process.py", line 1784, in __call__
    suppress_token_mask = torch.isin(vocab_tensor, self.begin_suppress_tokens)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
NotImplementedError: The operator 'aten::isin.Tensor_Tensor_out' is not currently implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on https://github.com/pytorch/pytorch/issues/77764. As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.

[grimelda]

Duplicate of issue @225 where @BaronZack proposed this solution to switch to nightly torch build , also mentioned in pytorch/pytorch#124518 so will soon be fixed in stable version