Fix extractor and gating tests

[LemurPwned]

Summary

• restore generate_segments in KeywordExtractor
• ensure ClipGate dependencies raise ImportError
• fix test using monkeypatch.setitem

Testing

• black tests/test_audio_extractor.py video_sampler/language/keyword_capture.py video_sampler/gating.py
• isort tests/test_audio_extractor.py video_sampler/language/keyword_capture.py video_sampler/gating.py

Summary by Sourcery

Introduce audio-powered keyword extraction using Whisper, enforce dependency checks for the Clip gate, and update documentation and tests accordingly.

New Features:

• Add AudioKeywordExtractor for audio-based keyword extraction via Whisper
• Extend create_extractor to support the new audio_keyword extractor type

Bug Fixes:

• Ensure gating create_model raises ImportError when open_clip or torch are missing

Enhancements:

• Simplify KeywordExtractor.generate_segments docstring
• Re-export KeywordExtractor and AudioKeywordExtractor in language package init

Documentation:

• Document audio-based keyword extraction usage in README

Tests:

• Add test to verify ImportError when Whisper is unavailable for AudioKeywordExtractor

[sourcery-ai]

Reviewer's Guide

Extends KeywordExtractor with an audio-based subclass using Whisper (with ImportError guards), simplifies the generate_segments docstring, updates the extractor factory and exports, enforces missing dependency errors in gating, refreshes the README CLI example, and adds a test for the Whisper import dependency.

File-Level Changes

Change	Details	Files
Simplify generate_segments docstring	Replace verbose multiline docstring with concise one	video_sampler/language/keyword_capture.py
Add AudioKeywordExtractor subclass with Whisper support	Import Whisper with ImportError guard in init Load Whisper model via whisper.load_model Implement transcribe method converting segments to subtitle list Add generate_segments_from_audio delegating to base generate_segments	video_sampler/language/keyword_capture.py video_sampler/language/__init__.py
Extend extractor factory for audio_keyword	Add audio_keyword branch in create_extractor to return AudioKeywordExtractor	video_sampler/language/keyword_capture.py
Enforce dependency errors in gating.create_model	Check for open_clip and torch in globals Raise ImportError when dependencies are missing	video_sampler/gating.py
Update README with audio extractor usage	Insert CLI example for segmenting based on audio transcription	README.md
Add test for Whisper dependency in AudioKeywordExtractor	Simulate missing whisper module via monkeypatch.setitem Assert ImportError is raised on initialization	tests/test_audio_extractor.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey @LemurPwned - I've reviewed your changes - here's some feedback:

• Rather than checking for open_clip and torch in globals(), wrap their imports in a try/except to more reliably detect missing dependencies.
• Consider refactoring create_extractor to use a dict mapping types to classes instead of chained if-statements, making it easier to add new extractors in the future.

Here's what I looked at during the review

• 🟡 General issues: 3 issues found
• 🟡 Testing: 1 issue found
• 🟢 Documentation: all looks good

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

suggestion: Trim whitespace from Whisper segment text

Call .strip() on seg['text'] to remove extra whitespace and prevent matching issues.

Suggested change

	for seg in result.get("segments", []):
	subtitle_list.append(
	((int(seg["start"] * 1000), int(seg["end"] * 1000)), seg["text"])
	)
	for seg in result.get("segments", []):
	subtitle_list.append(
	((int(seg["start"] * 1000), int(seg["end"] * 1000)), seg["text"].strip())
	)

[LemurPwned]

do not change the indents

[sourcery-ai]

Good point—let’s keep the existing indent structure and just call .strip() on the text. For example, if your current code looks like this:

for seg in result.get("segments", []):
    subtitle_list.append(
        ((int(seg["start"] * 1000), int(seg["end"] * 1000)),
         seg["text"])
    )

you can change it to:

for seg in result.get("segments", []):
    subtitle_list.append(
        ((int(seg["start"] * 1000), int(seg["end"] * 1000)),
         seg["text"].strip())
    )

This way you only trim the whitespace and don’t alter the indentation levels. Let me know if that aligns with your style rules!

[sourcery-ai]

suggestion (code-quality): Convert for loop into list comprehension (list-comprehension)

Suggested change

	subtitle_list: list[tuple[tuple[int, int], str]] = []
	for seg in result.get("segments", []):
	subtitle_list.append(
	((int(seg["start"] * 1000), int(seg["end"] * 1000)), seg["text"])
	)
	subtitle_list: list[tuple[tuple[int, int], str]] = [
	((int(seg["start"] * 1000), int(seg["end"] * 1000)), seg["text"])
	for seg in result.get("segments", [])
	]