fix(SpeechT5Config): missing annotation on inputs_to_logits_ratio property

[sw00]

What does this PR do?

Add the missing @property annotation on SpeechT5Config which causes failures on AutomaticSpeechRecognitionPipeline's preprocessing steps if chunk_length_s is specified.

Specifically, the following line of code will fail since getattr will resolve to a method instead of the value:

align_to = getattr(self.model.config, "inputs_to_logits_ratio", 1)

This stacktrace is generated on this error:

Traceback (most recent call last):
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/litserve/loops/simple_loops.py", line 88, in run_single_loop
    y = _inject_context(
        ^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/litserve/loops/base.py", line 48, in _inject_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/src/omniserve/api.py", line 19, in predict
    return self.model.predict(audio_data)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/src/omniserve/model.py", line 63, in predict
    output = self.pipeline(input)
             ^^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 275, in __call__
    return super().__call__(inputs, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/transformers/pipelines/base.py", line 1459, in __call__
    return next(
           ^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/transformers/pipelines/pt_utils.py", line 126, in __next__
    item = next(self.iterator)
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/transformers/pipelines/pt_utils.py", line 271, in __next__
    processed = self.infer(next(self.iterator), **self.params)
                           ^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/torch/utils/data/dataloader.py", line 734, in __next__
    data = self._next_data()
           ^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/torch/utils/data/dataloader.py", line 790, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/fetch.py", line 33, in fetch
    data.append(next(self.dataset_iter))
                ^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/transformers/pipelines/pt_utils.py", line 188, in __next__
    processed = next(self.subiterator)
                ^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/sett/src/model-cloud/servers/omniserve/.venv/lib/python3.12/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 450, in preprocess
    chunk_len = int(round(chunk_length_s * self.feature_extractor.sampling_rate / align_to) * align_to)
                          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~
TypeError: unsupported operand type(s) for /: 'float' and 'method'

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@Rocketknight1 @eustlb

[Rocketknight1]

Yep, this is an obvious bug. Thank you for the fix!

[Rocketknight1]

Not sure why CircleCI is failing - @ydshieh can you force-merge this? It's a one-line fix that shouldn't cause problems.

[github-actions]

[For maintainers] Suggested jobs to run (before merge)

run-slow: speecht5