audium-md 0.1.0__tar.gz

audium_md-0.1.0/.gitignore

@@ -0,0 +1,17 @@
+.venv/
+__pycache__/
+*.pyc
+*.pyo
+.pytest_cache/
+dist/
+*.egg-info/
+*.egg
+transcripts/
+.DS_Store
+
+# Agent and IDE artifacts
+.deepseek/
+.codewhale/
+.agents/
+.superpowers/
+STATE_DIR/

audium_md-0.1.0/PKG-INFO

@@ -0,0 +1,226 @@
+Metadata-Version: 2.4
+Name: audium-md
+Version: 0.1.0
+Summary: Audio-to-Markdown transcription optimized for AI consumption
+Author: tamukj
+License: MIT
+Requires-Python: >=3.10
+Requires-Dist: click>=8.1.0
+Requires-Dist: faster-whisper>=1.2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.0.0
+Provides-Extra: dev
+Requires-Dist: pytest-cov>=5.0; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <a href="https://github.com/Tamukj/Audium">
+    <img src="assets/logo.svg" width="180" alt="Audium logo">
+  </a>
+</p>
+
+<h1 align="center">Audium</h1>
+
+<p align="center">
+  <strong>🎧 Audio → AI‑optimized Markdown</strong>
+  <br>
+  <sub>Transcribe MP3/WAV/FLAC into clean, token‑efficient Markdown — ready for any LLM.</sub>
+</p>
+
+<p align="center">
+  <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10%2B-blue?style=flat&logo=python&logoColor=white" alt="Python 3.10+"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green?style=flat" alt="MIT License"></a>
+  <a href="https://pypi.org/project/audium-md/"><img src="https://img.shields.io/badge/pypi-v0.1.0-blue?style=flat&logo=pypi&logoColor=white" alt="PyPI version"></a>
+  <a href="https://github.com/SYSTRAN/faster-whisper"><img src="https://img.shields.io/badge/backend-faster--whisper-8A2BE2?style=flat" alt="faster-whisper"></a>
+  <a href="https://github.com/Tamukj/Audium"><img src="https://img.shields.io/badge/platform-linux%20%7C%20macOS%20%7C%20windows-lightgrey?style=flat" alt="Platform"></a>
+</p>
+
+<p align="center">
+  <a href="README.md">English</a> ·
+  <a href="README.ru.md">Русский</a> ·
+  <a href="README.zh-CN.md">中文</a>
+</p>
+
+---
+
+<h2 align="center">✨ Why Audium?</h2>
+
+Feed audio to an LLM. Get answers. Simple.
+
+But raw transcripts burn tokens on noise: long timestamps, filler words,
+silent segments, markup that adds nothing.
+
+Audium turns speech into **the minimum viable Markdown**: every character
+counts, nothing wasted.
+
+<div align="center">
+
+| 🎯 | ⚡ | 🪙 | 👁️ | 🌍 |
+|---|---|---|---|---|
+| **3 formats** | **GPU‑accelerated** | **Token‑aware** | **Watch mode** | **~97 languages** |
+| compact, minimal, structured | 2–10× real‑time on CUDA | `[MM:SS]` + VAD + filler‑strip | drop files → auto‑transcribe | tiny to large‑v3 |
+
+</div>
+
+---
+
+<h2 align="center">📦 Install</h2>
+
+```bash
+pip install audium-md
+```
+
+> Requires `ffmpeg` on your system: `sudo apt install ffmpeg` / `brew install ffmpeg`
+
+---
+
+<h2 align="center">🚀 Quick Start</h2>
+
+```bash
+# Process a folder
+audium run ./my-recordings/
+
+# Single file
+audium run lecture.mp3
+
+# Watch folder — auto‑transcribe new files
+audium watch ./incoming/
+
+# See what you've transcribed
+audium list
+
+# Change model
+audium config set model large-v3
+```
+
+---
+
+<h2 align="center">📝 Formats</h2>
+
+### compact *(default)*
+
+```
+# lecture.mp3 (01:23:45)
+
+[00:00] Neural networks learn hierarchical representations
+[00:04] Each layer detects increasingly abstract features
+[00:08] Early layers find edges and textures
+[00:12] Later layers detect objects and scenes
+```
+
+### minimal
+
+```
+Neural networks learn hierarchical representations
+Each layer detects increasingly abstract features
+Early layers find edges and textures
+Later layers detect objects and scenes
+```
+
+### structured *(requires speaker diarization)*
+
+```
+# interview.mp3 (00:45:12)
+
+## Alice [00:00-00:30]
+Neural networks are a powerful tool. It's important to understand their limitations.
+
+## Bob [00:30-01:15]
+I completely agree. Let me walk through an example to make this concrete.
+```
+
+---
+
+<h2 align="center">⚙️ Commands</h2>
+
+| Command | Description |
+|---------|-------------|
+| `audium run <path>` | Transcribe audio files or folders |
+| `audium watch <path>` | Watch folder and auto‑process new files |
+| `audium list [dir]` | Show processed transcripts with file sizes |
+| `audium config` | Show current configuration |
+| `audium config set <key> <value>` | Change a setting |
+| `audium config reset` | Reset to factory defaults |
+| `audium config path` | Show config file location |
+
+### Common flags for `run` and `watch`
+
+| Flag | Default | Description |
+|------|---------|-------------|
+| `-o, --output-dir` | `./transcripts` | Where to save .md files |
+| `-f, --format` | `compact` | `compact` / `minimal` / `structured` |
+| `-r, --recursive` | off | Search subdirectories |
+| `--model` | `small` | `tiny` / `base` / `small` / `medium` / `large-v3` |
+| `--language` | `auto` | Force language code: `ru`, `en`, `zh`, ... |
+| `--strip-fillers` | off | Remove "um", "uh", "like", "мм", "ээ", etc. |
+| `--no-vad` | off | Disable voice activity detection |
+| `--no-progress` | off | Hide the progress bar |
+
+---
+
+<h2 align="center">🔧 Configuration</h2>
+
+Settings are merged: **CLI flags > `.audium.yaml` (project) > `~/.config/audium/config.yaml` > defaults**
+
+```bash
+# Set default model
+audium config set model large-v3
+
+# Always strip filler words
+audium config set strip_fillers true
+
+# Custom output folder
+audium config set output_dir ~/Documents/transcripts
+
+# See what you changed
+audium config
+```
+
+```yaml
+# Example .audium.yaml (place in project root)
+model: medium
+language: ru
+format: minimal
+output_dir: ./transcripts
+```
+
+---
+
+<h2 align="center">🪙 Token Optimization</h2>
+
+Audium is built to minimize LLM token cost:
+
+| Technique | Savings |
+|-----------|---------|
+| `[MM:SS]` instead of `[HH:MM:SS.mmm]` | ~30% on timestamps |
+| VAD filtering (skip silence) | 15–40% on meeting recordings |
+| Filler‑word stripping | 5–10% on conversational speech |
+| `min_segment_duration` threshold | skip noise fragments |
+| One line per segment, no blank lines | ~8% vs paragraph output |
+
+---
+
+<h2 align="center">📊 Model Sizes</h2>
+
+| Model | Parameters | Speed (GPU) | Best for |
+|-------|-----------|-------------|----------|
+| tiny | 39M | ~32× real‑time | Quick drafts, low‑resource |
+| base | 74M | ~16× real‑time | Dictation, clean audio |
+| small | 244M | ~6× real‑time | **General purpose** |
+| medium | 769M | ~2× real‑time | Accents, noisy audio |
+| large‑v3 | 1.5B | ~1× real‑time | Maximum accuracy |
+
+> All multilingual models support the same ~97 languages. The size trades accuracy for speed.
+
+---
+
+<h2 align="center">📄 License</h2>
+
+<p align="center">
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=for-the-badge" alt="MIT License"></a>
+</p>
+
+<p align="center">
+  MIT — do whatever you want. Attribution appreciated.
+</p>

audium_md-0.1.0/README.md

@@ -0,0 +1,210 @@
+<p align="center">
+  <a href="https://github.com/Tamukj/Audium">
+    <img src="assets/logo.svg" width="180" alt="Audium logo">
+  </a>
+</p>
+
+<h1 align="center">Audium</h1>
+
+<p align="center">
+  <strong>🎧 Audio → AI‑optimized Markdown</strong>
+  <br>
+  <sub>Transcribe MP3/WAV/FLAC into clean, token‑efficient Markdown — ready for any LLM.</sub>
+</p>
+
+<p align="center">
+  <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10%2B-blue?style=flat&logo=python&logoColor=white" alt="Python 3.10+"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green?style=flat" alt="MIT License"></a>
+  <a href="https://pypi.org/project/audium-md/"><img src="https://img.shields.io/badge/pypi-v0.1.0-blue?style=flat&logo=pypi&logoColor=white" alt="PyPI version"></a>
+  <a href="https://github.com/SYSTRAN/faster-whisper"><img src="https://img.shields.io/badge/backend-faster--whisper-8A2BE2?style=flat" alt="faster-whisper"></a>
+  <a href="https://github.com/Tamukj/Audium"><img src="https://img.shields.io/badge/platform-linux%20%7C%20macOS%20%7C%20windows-lightgrey?style=flat" alt="Platform"></a>
+</p>
+
+<p align="center">
+  <a href="README.md">English</a> ·
+  <a href="README.ru.md">Русский</a> ·
+  <a href="README.zh-CN.md">中文</a>
+</p>
+
+---
+
+<h2 align="center">✨ Why Audium?</h2>
+
+Feed audio to an LLM. Get answers. Simple.
+
+But raw transcripts burn tokens on noise: long timestamps, filler words,
+silent segments, markup that adds nothing.
+
+Audium turns speech into **the minimum viable Markdown**: every character
+counts, nothing wasted.
+
+<div align="center">
+
+| 🎯 | ⚡ | 🪙 | 👁️ | 🌍 |
+|---|---|---|---|---|
+| **3 formats** | **GPU‑accelerated** | **Token‑aware** | **Watch mode** | **~97 languages** |
+| compact, minimal, structured | 2–10× real‑time on CUDA | `[MM:SS]` + VAD + filler‑strip | drop files → auto‑transcribe | tiny to large‑v3 |
+
+</div>
+
+---
+
+<h2 align="center">📦 Install</h2>
+
+```bash
+pip install audium-md
+```
+
+> Requires `ffmpeg` on your system: `sudo apt install ffmpeg` / `brew install ffmpeg`
+
+---
+
+<h2 align="center">🚀 Quick Start</h2>
+
+```bash
+# Process a folder
+audium run ./my-recordings/
+
+# Single file
+audium run lecture.mp3
+
+# Watch folder — auto‑transcribe new files
+audium watch ./incoming/
+
+# See what you've transcribed
+audium list
+
+# Change model
+audium config set model large-v3
+```
+
+---
+
+<h2 align="center">📝 Formats</h2>
+
+### compact *(default)*
+
+```
+# lecture.mp3 (01:23:45)
+
+[00:00] Neural networks learn hierarchical representations
+[00:04] Each layer detects increasingly abstract features
+[00:08] Early layers find edges and textures
+[00:12] Later layers detect objects and scenes
+```
+
+### minimal
+
+```
+Neural networks learn hierarchical representations
+Each layer detects increasingly abstract features
+Early layers find edges and textures
+Later layers detect objects and scenes
+```
+
+### structured *(requires speaker diarization)*
+
+```
+# interview.mp3 (00:45:12)
+
+## Alice [00:00-00:30]
+Neural networks are a powerful tool. It's important to understand their limitations.
+
+## Bob [00:30-01:15]
+I completely agree. Let me walk through an example to make this concrete.
+```
+
+---
+
+<h2 align="center">⚙️ Commands</h2>
+
+| Command | Description |
+|---------|-------------|
+| `audium run <path>` | Transcribe audio files or folders |
+| `audium watch <path>` | Watch folder and auto‑process new files |
+| `audium list [dir]` | Show processed transcripts with file sizes |
+| `audium config` | Show current configuration |
+| `audium config set <key> <value>` | Change a setting |
+| `audium config reset` | Reset to factory defaults |
+| `audium config path` | Show config file location |
+
+### Common flags for `run` and `watch`
+
+| Flag | Default | Description |
+|------|---------|-------------|
+| `-o, --output-dir` | `./transcripts` | Where to save .md files |
+| `-f, --format` | `compact` | `compact` / `minimal` / `structured` |
+| `-r, --recursive` | off | Search subdirectories |
+| `--model` | `small` | `tiny` / `base` / `small` / `medium` / `large-v3` |
+| `--language` | `auto` | Force language code: `ru`, `en`, `zh`, ... |
+| `--strip-fillers` | off | Remove "um", "uh", "like", "мм", "ээ", etc. |
+| `--no-vad` | off | Disable voice activity detection |
+| `--no-progress` | off | Hide the progress bar |
+
+---
+
+<h2 align="center">🔧 Configuration</h2>
+
+Settings are merged: **CLI flags > `.audium.yaml` (project) > `~/.config/audium/config.yaml` > defaults**
+
+```bash
+# Set default model
+audium config set model large-v3
+
+# Always strip filler words
+audium config set strip_fillers true
+
+# Custom output folder
+audium config set output_dir ~/Documents/transcripts
+
+# See what you changed
+audium config
+```
+
+```yaml
+# Example .audium.yaml (place in project root)
+model: medium
+language: ru
+format: minimal
+output_dir: ./transcripts
+```
+
+---
+
+<h2 align="center">🪙 Token Optimization</h2>
+
+Audium is built to minimize LLM token cost:
+
+| Technique | Savings |
+|-----------|---------|
+| `[MM:SS]` instead of `[HH:MM:SS.mmm]` | ~30% on timestamps |
+| VAD filtering (skip silence) | 15–40% on meeting recordings |
+| Filler‑word stripping | 5–10% on conversational speech |
+| `min_segment_duration` threshold | skip noise fragments |
+| One line per segment, no blank lines | ~8% vs paragraph output |
+
+---
+
+<h2 align="center">📊 Model Sizes</h2>
+
+| Model | Parameters | Speed (GPU) | Best for |
+|-------|-----------|-------------|----------|
+| tiny | 39M | ~32× real‑time | Quick drafts, low‑resource |
+| base | 74M | ~16× real‑time | Dictation, clean audio |
+| small | 244M | ~6× real‑time | **General purpose** |
+| medium | 769M | ~2× real‑time | Accents, noisy audio |
+| large‑v3 | 1.5B | ~1× real‑time | Maximum accuracy |
+
+> All multilingual models support the same ~97 languages. The size trades accuracy for speed.
+
+---
+
+<h2 align="center">📄 License</h2>
+
+<p align="center">
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=for-the-badge" alt="MIT License"></a>
+</p>
+
+<p align="center">
+  MIT — do whatever you want. Attribution appreciated.
+</p>

audium_md-0.1.0/README.ru.md

@@ -0,0 +1,210 @@
+<p align="center">
+  <a href="https://github.com/Tamukj/Audium">
+    <img src="assets/logo.svg" width="180" alt="Audium logo">
+  </a>
+</p>
+
+<h1 align="center">Audium</h1>
+
+<p align="center">
+  <strong>🎧 Аудио → Markdown, оптимизированный для ИИ</strong>
+  <br>
+  <sub>Транскрибируйте MP3/WAV/FLAC в чистый, токен‑эффективный Markdown — готовый для любого LLM.</sub>
+</p>
+
+<p align="center">
+  <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10%2B-blue?style=flat&logo=python&logoColor=white" alt="Python 3.10+"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green?style=flat" alt="MIT License"></a>
+  <a href="https://pypi.org/project/audium-md/"><img src="https://img.shields.io/badge/pypi-v0.1.0-blue?style=flat&logo=pypi&logoColor=white" alt="PyPI version"></a>
+  <a href="https://github.com/SYSTRAN/faster-whisper"><img src="https://img.shields.io/badge/backend-faster--whisper-8A2BE2?style=flat" alt="faster-whisper"></a>
+  <a href="https://github.com/Tamukj/Audium"><img src="https://img.shields.io/badge/platform-linux%20%7C%20macOS%20%7C%20windows-lightgrey?style=flat" alt="Platform"></a>
+</p>
+
+<p align="center">
+  <a href="README.md">English</a> ·
+  <a href="README.ru.md">Русский</a> ·
+  <a href="README.zh-CN.md">中文</a>
+</p>
+
+---
+
+<h2 align="center">✨ Зачем Audium?</h2>
+
+Скормить аудио LLM и получить ответ. Просто.
+
+Но сырые транскрипты сжигают токены на шум: длинные таймкоды,
+слова‑паразиты, пустые сегменты, разметка, которая ничего не добавляет.
+
+Audium превращает речь в **минимально достаточный Markdown**: каждый символ
+на счету, ничего лишнего.
+
+<div align="center">
+
+| 🎯 | ⚡ | 🪙 | 👁️ | 🌍 |
+|---|---|---|---|---|
+| **3 формата** | **GPU‑ускорение** | **Оптимизация токенов** | **Режим наблюдения** | **~97 языков** |
+| compact, minimal, structured | 2–10× реал. времени на CUDA | `[MM:SS]` + VAD + очистка паразитов | закинул файлы → авто‑транскрибация | tiny до large‑v3 |
+
+</div>
+
+---
+
+<h2 align="center">📦 Установка</h2>
+
+```bash
+pip install audium-md
+```
+
+> Требуется `ffmpeg` на системе: `sudo apt install ffmpeg` / `brew install ffmpeg`
+
+---
+
+<h2 align="center">🚀 Быстрый старт</h2>
+
+```bash
+# Обработать папку
+audium run ./my-recordings/
+
+# Один файл
+audium run lecture.mp3
+
+# Следить за папкой — авто‑транскрибация новых файлов
+audium watch ./incoming/
+
+# Посмотреть что уже обработано
+audium list
+
+# Сменить модель
+audium config set model large-v3
+```
+
+---
+
+<h2 align="center">📝 Форматы</h2>
+
+### compact *(по умолчанию)*
+
+```
+# lecture.mp3 (01:23:45)
+
+[00:00] Нейронные сети обучаются иерархическим представлениям
+[00:04] Каждый слой выявляет всё более абстрактные признаки
+[00:08] На ранних слоях — грани и текстуры
+[00:12] На поздних — объекты и сцены
+```
+
+### minimal
+
+```
+Нейронные сети обучаются иерархическим представлениям
+Каждый слой выявляет всё более абстрактные признаки
+На ранних слоях — грани и текстуры
+На поздних — объекты и сцены
+```
+
+### structured *(требуется диаризация спикеров)*
+
+```
+# interview.mp3 (00:45:12)
+
+## Alice [00:00-00:30]
+Нейронные сети — мощный инструмент. Важно понимать их ограничения.
+
+## Bob [00:30-01:15]
+Полностью согласен. Давайте разберём конкретный пример.
+```
+
+---
+
+<h2 align="center">⚙️ Команды</h2>
+
+| Команда | Описание |
+|---------|----------|
+| `audium run <путь>` | Транскрибировать аудиофайлы или папки |
+| `audium watch <путь>` | Следить за папкой и авто‑обрабатывать новые файлы |
+| `audium list [папка]` | Показать обработанные транскрипты с размерами |
+| `audium config` | Показать текущую конфигурацию |
+| `audium config set <ключ> <значение>` | Изменить настройку |
+| `audium config reset` | Сбросить к заводским значениям |
+| `audium config path` | Показать путь к файлу конфигурации |
+
+### Основные флаги для `run` и `watch`
+
+| Флаг | По умолчанию | Описание |
+|------|-------------|----------|
+| `-o, --output-dir` | `./transcripts` | Куда сохранять .md файлы |
+| `-f, --format` | `compact` | `compact` / `minimal` / `structured` |
+| `-r, --recursive` | выкл | Искать в подпапках |
+| `--model` | `small` | `tiny` / `base` / `small` / `medium` / `large-v3` |
+| `--language` | `auto` | Код языка: `ru`, `en`, `zh`, ... |
+| `--strip-fillers` | выкл | Удалять «мм», «ээ», «типа», «um», «uh» и т.д. |
+| `--no-vad` | выкл | Отключить VAD (voice activity detection) |
+| `--no-progress` | выкл | Скрыть прогресс‑бар |
+
+---
+
+<h2 align="center">🔧 Конфигурация</h2>
+
+Настройки объединяются: **флаги CLI > `.audium.yaml` (проект) > `~/.config/audium/config.yaml` > значения по умолчанию**
+
+```bash
+# Модель по умолчанию
+audium config set model large-v3
+
+# Всегда удалять слова‑паразиты
+audium config set strip_fillers true
+
+# Своя папка для вывода
+audium config set output_dir ~/Documents/transcripts
+
+# Посмотреть изменения
+audium config
+```
+
+```yaml
+# Пример .audium.yaml (в корне проекта)
+model: medium
+language: ru
+format: minimal
+output_dir: ./transcripts
+```
+
+---
+
+<h2 align="center">🪙 Оптимизация токенов</h2>
+
+Audium создан чтобы минимизировать расход токенов LLM:
+
+| Техника | Экономия |
+|---------|----------|
+| `[MM:SS]` вместо `[HH:MM:SS.mmm]` | ~30% на таймкодах |
+| VAD‑фильтр (пропуск тишины) | 15–40% на записях встреч |
+| Удаление слов‑паразитов | 5–10% на разговорной речи |
+| Порог `min_segment_duration` | пропуск шумовых фрагментов |
+| Одна строка на сегмент, без пустых строк | ~8% по сравнению с абзацами |
+
+---
+
+<h2 align="center">📊 Размеры моделей</h2>
+
+| Модель | Параметров | Скорость (GPU) | Для чего |
+|--------|-----------|----------------|----------|
+| tiny | 39M | ~32× реал. времени | Черновики, слабые машины |
+| base | 74M | ~16× реал. времени | Диктовка, чистое аудио |
+| small | 244M | ~6× реал. времени | **Универсальная** |
+| medium | 769M | ~2× реал. времени | Акценты, шумное аудио |
+| large‑v3 | 1.5B | ~1× реал. времени | Максимальная точность |
+
+> Все мультиязычные модели поддерживают одни и те же ~97 языков. Размер влияет на точность и скорость.
+
+---
+
+<h2 align="center">📄 Лицензия</h2>
+
+<p align="center">
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=for-the-badge" alt="MIT License"></a>
+</p>
+
+<p align="center">
+  MIT — делайте что хотите. Ссылка на автора приветствуется.
+</p>