# My local LLM suggested 27 references. Only 7 passed verification.

> Source: <https://dev.to/drakenmario/my-local-llm-suggested-27-references-only-7-passed-verification-4nm9>
> Published: 2026-11-18 22:06:56+00:00

**Recommendation:** Before publishing LLM-suggested references, match each author, title, and year against Open Library or Crossref and cite the catalog's metadata; in the source, only 7 of 27 proposals verified.
More in the playbook "Verifying model output": <https://wpnews.pro/playbooks/output-verification>

I record a lot of lectures and meetings, but I almost never watch them again.

What I actually want afterward is something I can read: a summary of what was discussed, the main topics, and any books or papers that were mentioned.

So I started building [vtd (video-to-doc)](https://github.com/Mariotutal/video-to-doc), an open-source CLI that turns audio and video recordings into structured Markdown or PDF documents.

At some point, I thought it would be useful to have the AI identify books and academic papers mentioned in a recording.

That sounded like a fairly straightforward feature.

Then I tested it with a real two-hour lecture.

My local model (`qwen3.6:35b` running through Ollama) suggested **27 references. I could only verify 7 of them** against Open Library and Crossref.

That test led me to add a catalog verification step before a reference can appear in the final document.

The basic idea is simple. Give it a recording:

```
vtd lecture.mp4
```

Without enabling AI, vtd uses `whisper.cpp` to transcribe the recording, splits it into sections based on pauses, extracts frames from the video, and generates a document combining everything.

It works locally, without an API key.

If you add `--with-ai`, a language model generates notes that include:

You can use a hosted model or a local one through Ollama.

I use Ollama to run the model locally.

I added a `--references` flag.

When enabled, the model identifies two types of works:

For each one, it proposes an author, title, and publication year.

But instead of trusting that information, vtd searches two public catalogs:

To accept a reference, vtd checks that:

For example, `Vygotsky` and `Vygotskiĭ` can still match.

The final citation uses **the catalog’s metadata**.

To organize the bibliography, vtd checks the relevant transcript section for the author’s capitalized surname or a title of at least four words. It lists verified works with transcript evidence under **Works referred to in the recording** and other verified suggestions under **Further reading**.

I added a reproducible example to the repository.

I used President Kennedy's 1962 speech at Rice University, an 18-minute public-domain recording.

Here's the command:

```
vtd rice-speech.ogg \
  --language en \
  --whisper-model large-v3-turbo \
  --with-ai \
  --provider ollama \
  --ai-model qwen3.6:35b \
  --content-type lecture \
  --references \
  --pdf
```

I ran it on a Mac with an M4 Pro and 48 GB of memory.

The results:

| Step | Time | 
|---|---|
| Processing without AI | 36 seconds | 
| AI notes, references, and PDF | 101 additional seconds | 

The Whisper model was already downloaded.

These timings are from a single run.

One of the eight proposed works matched a catalog record and appeared in the bibliography as further reading.

**Works referred to in the recording**

*None detected.*

**Further reading (not mentioned in the recording)**

The project is open source and MIT-licensed:

**GitHub:** [https://github.com/Mariotutal/video-to-doc](https://github.com/Mariotutal/video-to-doc)

If you work with recorded lectures, meetings, or presentations, feel free to give it a try.

I’d be interested to hear how you use it with your own recordings. Share your experience in the comments or open an issue on GitHub.
