taters 0.1.7

Analyze, process, and extract from many types of input data. Highly modular/customizable.

🥔 TATERS: Takes All Things, Extracts Relevant Stuff

Taters is a Python toolkit (and CLI) for getting from raw media to analysis-ready artifacts — fast, repeatable, and with predictable outputs. Point it at video, audio, or text and it helps you build end-to-end workflows: extract WAV from video, diarize and transcribe, compute embeddings, run dictionary/archetype analyses, then gather everything into tidy datasets you can model or visualize.

• 🥔 Documentation: https://www.taters.wiki
• 🥔 Status: early but usable; APIs will probably evolve. Pin versions if you need stability.

---

What Taters is (and is not)

• Is: A library + CLI with small, composable functions and an optional YAML pipeline runner. Predictable I/O, friendly defaults, and “do not overwrite unless asked.”
• Is not: A single black-box pipeline. You keep control of each step and can run pieces à la carte or all at once.
• Is not: Edible.

---

A tiny taste of Taters

Python

from taters import Taters
t = Taters()

# Pull audio from video
wavs = t.audio.extract_wavs_from_video(input_path="input.mp4")

# Diarize & transcribe (CSV/SRT/TXT)
diar = t.audio.diarize_with_thirdparty(audio_path=wavs[0], device="auto")

# Features (defaults write under ./features/<kind>/)
t.audio.extract_whisper_embeddings(source_wav=wavs[0], transcript_csv=diar["csv"])
t.text.analyze_with_dictionaries(csv_path=diar["csv"], dict_paths=["dictionaries/liwc"])
t.text.analyze_with_archetypes(csv_path=diar["csv"], archetype_csvs=["archetypes/Resilience.csv"])

CLI

# Whisper embeddings over non-silent spans, then mean-pool
python -m taters.audio.extract_whisper_embeddings \
  --source_wav audio/session.wav --strategy nonsilent --aggregate mean

For more examples (including per-speaker splits, sentence embeddings, and end-to-end pipelines), see the Guides in the docs.

---

Installation

Use a fresh virtual environment. Then follow the step-by-step install guide (CPU or CUDA, FFmpeg, optional diarization extras): 👉 https://www.taters.wiki/install-guide

---

Pipelines

When you are ready to batch a whole dataset, use the YAML runner to chain steps and control concurrency:

python -m taters.pipelines.run_pipeline \
  --root_dir videos --file_type video \
  --preset conversation_video \
  --workers 8 --var device=cuda

Details, presets, and how to write your own: 👉 https://www.taters.wiki/guides/pipelines/

---

Contributing

Bug reports and pull requests are welcome. If you are using Taters on real projects, feedback on rough edges and missing presets is especially valuable.

---

License

MIT. See LICENSE for details.