Caching

The summarizer keeps an in-memory transcript cache so you can re-process the same video with different styles, providers, or languages without waiting for transcription again.

How It Works

When you run the CLI or webapp:

1. A cache key is built from the parameters that affect transcription output
2. If a matching transcript exists in memory, it is returned instantly
3. On a cache miss, the transcript is fetched normally and stored for later reuse

Cache hits are reported in verbose mode:

[+] Transcript cache hit (a3f7b2d8e1c4) — skipping transcription

Cache Key

The key is a SHA-256 hash of these parameters joined together:

Changing any of these values produces a different key and triggers a fresh transcription. Changing the summary style, provider, or output language does not affect the key, so those re-runs are instant.

Disabling the Cache

Set cache-transcript: false in summarizer.yaml:

1
defaults:
2
  cache-transcript: false

Or pass --no-config and the cache is bypassed entirely.

Important Notes

• The cache lives in process memory only and is cleared when the process exits.
• There is no disk persistence. Restarting the CLI or the Streamlit server starts with an empty cache.
• The cache does not apply to visual mode (--visual), which skips transcription entirely.
• The cache applies to TXT files too, since they bypass audio processing and are treated as pre-existing transcripts.