Follow-up to v0.5.2, from measuring the fix instead of trusting it. Asking the
running install for word timings on 4.3 seconds of Italian it had just
synthesised showed two more faults in the same chain, both of which answer 200
with the timings missing.

A CTC pipeline cannot take `generate_kwargs=None`: it iterates it and raises
`TypeError: 'NoneType' object is not iterable`. The backend passed exactly
that whenever a model had no generate kwargs, which is every wav2vec2/MMS
checkpoint -- and the retry below it then turned the failure into a text-only
success, so the only trace was one line in the log. `wav2vec2-it` returned 0
words before this and the same 14 the pipeline always produced after. The
kwarg is now omitted when empty rather than passed as None.

And the pick has to consider the language, not just the backend: a model that
declares `languages` REFUSES the rest with a 400, so an install with
`wav2vec2-it` and `wav2vec2-en` has two models that each report word timings
and each reject the other's language. Picking one for the wrong language would
have replaced one silent fallback with another.

Measured, on sixteen configured audio models: ten cannot time words at all.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S8LAP3ueNzQJtwzhgVbq66