feat(whisper): Add diarization (tinydiarize)

[richiejp]

Description

This exposes Whispers tdrz option which enables speaker segmentation. It only works with the small.en-tdrz whisper model.

When enabled it produces output like the following (taken from Whisper CPP's README):

[00:00:00.000 --> 00:00:03.800]   Okay Houston, we've had a problem here. [SPEAKER_TURN]
[00:00:03.800 --> 00:00:06.200]   This is Houston. Say again please. [SPEAKER_TURN]
[00:00:06.200 --> 00:00:08.260]   Uh Houston we've had a problem.
[00:00:08.260 --> 00:00:11.320]   We've had a main beam up on a volt. [SPEAKER_TURN]
[00:00:11.320 --> 00:00:13.820]   Roger main beam interval. [SPEAKER_TURN]
[00:00:13.820 --> 00:00:15.100]   Uh uh [SPEAKER_TURN]
[00:00:15.100 --> 00:00:18.020]   So okay stand, by thirteen we're looking at it. [SPEAKER_TURN]
[00:00:18.020 --> 00:00:25.740]   Okay uh right now uh Houston the uh voltage is uh is looking good um.
[00:00:27.620 --> 00:00:29.940]   And we had a a pretty large bank or so.

It can be enabled by passing the -d or --diarize flags to the CLI or by setting diarize: true on JSON HTTP requests.

Notes for Reviewers

Fixes #3374

Signed commits

• Yes, I signed my commits.

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	0e7e34e
🔍 Latest deploy log	https://app.netlify.com/projects/localai/deploys/68c00ac6608c390008ed0d6c
😎 Deploy Preview	https://deploy-preview-6184--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[richiejp]

I removed the fixes for #1648 because that ticket mentions a bunch of stuff that is way more feature rich than tinydiarize. This only tells us that the speaker has changed, but we don't an embedding identifying the speaker or anything like that.