German Learning — Co-learning Context Repo

This repo tracks what I've actually covered across German-learning materials (course books, workbooks, audio transcripts, and answer keys), lesson by lesson, so that Claude (or any LLM) has exact context on my vocabulary and grammar level when we study together. Menschen A1.1 is the first source; later books can be added alongside it.

How to use this with Claude

At the start of a study session, point Claude at the relevant lesson file(s) (e.g. A1.1/lektion-05.md), or the whole A1.1/INDEX.md for a running summary. Ask Claude to only use vocabulary/grammar that appears in those files (or earlier lessons) when creating exercises, example sentences, or corrections — this keeps practice within what I've actually learned.

Structure

A1.1/
  lektion-XX.md   ← everything for one lesson: vocab, grammar, communication
                     patterns, course book + workbook exercise summaries,
                     official audio transcripts, answer key highlights
  _template.md    ← template used to build each lektion-XX.md
  INDEX.md        ← one-line summary of every lesson so far
A1.2/             ← added once I move on to the next book
  ...
Ergaenzung/       ← supplementary practice books (see below)
  wortschatz-grammatik-a1/
  hoeren-sprechen-a1/
  lesen-schreiben-a1/
  _template.md
  INDEX.md
scripts/
  transcribe.py   ← local ASR fallback (faster-whisper) for audio with no
                     official transcript

Each lesson is one combined file rather than separate course-book/workbook files, because Menschen's workbook exercises constantly reference course book sections (e.g. "KB 2b") and share the same grammar — splitting them apart would just duplicate content.

Adding a new lesson

1. Get the course book pages, workbook pages, and (if available) the official Hueber Transkriptionen PDF pages for that lesson — as PDFs, photos, or a folder path.
2. Claude extracts/summarizes content into lektion-XX.md using _template.md: vocabulary (from the workbook's Lernwortschatz page), grammar boxes, communication patterns, a brief summary of what each exercise practices (not full exercise text), audio transcripts, and answer key highlights.
3. Review and correct anything Claude got wrong or over-summarized.
4. Update INDEX.md with a one-line entry for the lesson.
5. Commit.

Audio (listening exercises)

Hueber releases official Transkriptionen PDFs for both the Kursbuch (course book) and Arbeitsbuch (workbook) — these are the primary source for audio content, not the Lösungsschlüssel (answer key — a different document). Raw audio files are not stored in this repo (see .gitignore); only transcripts (text) are, since that's what gives Claude context.

Primary workflow — official transcripts:

1. Get the Kursbuch and Arbeitsbuch Transkriptionen PDFs for the relevant book (A1.1, A1.2, ...).
2. Extract the per-track dialogue text into that lesson's .md file under "Audio / Listening", marked as official-sourced.
3. No review needed for accuracy — these are publisher-official text, not ASR.

Fallback workflow — local ASR (only if no official transcript exists for a given track, e.g. supplementary listening material):

1. Get the audio files locally (publisher CD/app/download), any folder outside git.
2. Run scripts/transcribe.py (uses faster-whisper on GPU) to transcribe them:

   pip install faster-whisper
   python scripts/transcribe.py "<path-to-lesson-audio>" "A1.1/transcripts/lektion-XX"
   

3. Skim the .txt output for ASR mistakes (names, numbers, fast speech) and fix them.
4. Reference/paste the transcript into the lesson's .md file under "Audio / Listening", flagged as ASR-generated — transcripts are small text files so committing them is fine.

Adding a new book (e.g. A1.2)

Copy the A1.1/ folder structure (minus content) into a new A1.2/ folder and repeat the process.

Supplementary practice books (Ergaenzung/)

Alongside Menschen, I also use three Hueber Deutsch üben practice books: Wortschatz & Grammatik A1, Hören & Sprechen A1, and Lesen & Schreiben A1. Unlike Menschen, these aren't organized lesson-by-lesson against a shared story/curriculum — each is structured around its own topics/units (grammar points for Wortschatz & Grammatik, skill-practice units for the other two). Forcing them into the A1.1/lektion-XX.md structure would misrepresent that, so they get their own space instead:

Ergaenzung/
  wortschatz-grammatik-a1/abschnitt-X.md
  hoeren-sprechen-a1/abschnitt-X.md
  lesen-schreiben-a1/abschnitt-X.md
  _template.md   ← template for these files
  INDEX.md       ← per-book tables mapping each section to Menschen Lektion(en)

Each abschnitt-X.md covers one lettered section as defined by that book's own table of contents (e.g. Wortschatz & Grammatik A1's "A Person, Familie und Freunde", which itself bundles ~17 small sub-exercises) — not one file per tiny sub-exercise, since those are often half a page each. It's scoped like a lesson file (vocab/grammar covered, exercise summary, audio transcript if applicable, answer key highlights, notes) but adds a "Relates to Menschen Lektion(en)" field so a tutor session can tell whether content is reinforcing what's already been covered in Menschen or introducing something new/out-of-scope. These books also ship their own built-in Lösungen (answer key), so no separate answer-key source is needed.

Workflow for adding a section: same as adding a Menschen lesson (get the pages as PDF/photo, Claude summarizes into abschnitt-X.md using Ergaenzung/_template.md, review, update Ergaenzung/INDEX.md, commit).