audio-metrics-cli 0.1.0__tar.gz

audio_metrics_cli-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 OpenClaw
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

audio_metrics_cli-0.1.0/PKG-INFO

@@ -0,0 +1,296 @@
+Metadata-Version: 2.4
+Name: audio-metrics-cli
+Version: 0.1.0
+Summary: Cross-platform audio analysis toolkit for speech metrics extraction
+Author-email: OpenClaw <clawbot@openclaw.ai>
+License: MIT
+Project-URL: Homepage, https://github.com/i-whimsy/audio-metrics-cli
+Project-URL: Repository, https://github.com/i-whimsy/audio-metrics-cli.git
+Project-URL: Documentation, https://github.com/i-whimsy/audio-metrics-cli#readme
+Keywords: audio,speech,analysis,metrics,whisper,vad,prosody,cli
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23.0
+Requires-Dist: librosa>=0.10.0
+Requires-Dist: soundfile>=0.12.0
+Requires-Dist: openai-whisper>=20230314
+Requires-Dist: click>=8.1.0
+Requires-Dist: tqdm>=4.65.0
+Requires-Dist: pydantic>=2.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Provides-Extra: emotion
+Requires-Dist: torch>=2.0.0; extra == "emotion"
+Requires-Dist: torchaudio>=2.0.0; extra == "emotion"
+Requires-Dist: speechbrain>=0.5.14; extra == "emotion"
+Dynamic: license-file
+
+# Audio Metrics CLI
+
+🎙️ **Cross-platform audio analysis toolkit for speech metrics extraction**
+
+[![PyPI version](https://badge.fury.io/py/audio-metrics-cli.svg)](https://badge.fury.io/py/audio-metrics-cli)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+---
+
+## 🚀 Quick Start
+
+### Installation
+
+```bash
+# Install from PyPI (recommended)
+pip install audio-metrics-cli
+
+# Or install from source (development)
+git clone https://github.com/i-whimsy/audio-metrics-cli.git
+cd audio-metrics-cli
+pip install -e ".[dev]"
+```
+
+### Basic Usage
+
+```bash
+# Analyze audio file
+audio-metrics analyze your_audio.wav --output result.json
+
+# With verbose output
+audio-metrics analyze audio.mp3 --verbose --show-progress
+
+# Transcribe only
+audio-metrics transcribe audio.m4a -o transcript.txt
+
+# Compare two audio files
+audio-metrics compare v1.wav v2.wav
+```
+
+---
+
+## 📦 Features
+
+### Core Metrics
+
+- **🎵 Audio Information**: Duration, sample rate, file size
+- **🗣️ Voice Activity Detection**: Speech/silence segmentation
+- **📝 Speech-to-Text**: Whisper-powered transcription
+- **🎼 Prosody Analysis**: Pitch, energy, speech rate
+- **😊 Emotion Recognition**: Emotional state detection (optional)
+- **🔤 Filler Word Detection**: "um", "uh", "like" detection
+
+### Supported Formats
+
+- ✅ WAV
+- ✅ MP3
+- ✅ M4A
+- ✅ FLAC
+- ✅ OGG
+
+### Cross-Platform
+
+- ✅ Windows
+- ✅ macOS
+- ✅ Linux
+
+---
+
+## 📖 Documentation
+
+### Command Line Interface
+
+#### `analyze` - Full Analysis
+
+```bash
+audio-metrics analyze audio.wav [OPTIONS]
+
+Options:
+  -o, --output PATH        Output JSON file path
+  -c, --config PATH        Configuration file
+  -m, --model TEXT         Whisper model (tiny/base/small/medium/large)
+  --no-emotion            Skip emotion analysis
+  --show-progress         Show progress bars
+  -v, --verbose           Verbose output
+  --help                  Show this message
+```
+
+#### `transcribe` - Speech to Text
+
+```bash
+audio-metrics transcribe audio.wav [OPTIONS]
+
+Options:
+  -o, --output PATH       Output transcript file
+  -m, --model TEXT        Whisper model
+  --language TEXT         Language code
+  --help                  Show this message
+```
+
+#### `compare` - Compare Audio Files
+
+```bash
+audio-metrics compare audio1.wav audio2.wav [OPTIONS]
+
+Options:
+  --format TEXT          Output format (text/json/markdown)
+  --help                 Show this message
+```
+
+---
+
+## 📊 Output Example
+
+```json
+{
+  "audio_info": {
+    "duration_seconds": 185.2,
+    "sample_rate": 44100,
+    "file_size_mb": 2.8
+  },
+  "vad_analysis": {
+    "speech_ratio": 0.81,
+    "pause_count": 23,
+    "avg_pause_duration": 1.1
+  },
+  "speech_metrics": {
+    "words_total": 820,
+    "words_per_minute": 266
+  },
+  "prosody_metrics": {
+    "pitch_mean_hz": 145.3,
+    "energy_cv": 0.33
+  },
+  "filler_metrics": {
+    "filler_word_count": 18,
+    "fillers_per_100_words": 2.2
+  }
+}
+```
+
+---
+
+## 🔧 Configuration
+
+Create a `config.json` file:
+
+```json
+{
+  "models": {
+    "speech_to_text": {
+      "provider": "whisper",
+      "model": "base",
+      "device": "auto"
+    },
+    "vad": {
+      "provider": "silero",
+      "threshold": 0.5
+    }
+  },
+  "audio_analysis": {
+    "enable_pitch": true,
+    "enable_energy": true,
+    "enable_pause": true
+  },
+  "features": {
+    "enable_emotion": true,
+    "skip_if_too_long": 3600
+  }
+}
+```
+
+---
+
+## 💻 Development
+
+### Setup Development Environment
+
+```bash
+# Clone repository
+git clone https://github.com/i-whimsy/audio-metrics-cli.git
+cd audio-metrics-cli
+
+# Install with dev dependencies
+pip install -e ".[dev]"
+
+# Run tests
+pytest tests/
+
+# Format code
+black src/
+ruff check src/
+```
+
+### Project Structure
+
+```
+audio-metrics-cli/
+├── src/
+│   └── audio_metrics/
+│       ├── cli.py              # CLI entry point
+│       ├── config.py           # Configuration
+│       └── modules/            # Core modules
+│           ├── audio_loader.py
+│           ├── vad_analyzer.py
+│           ├── speech_to_text.py
+│           ├── prosody_analyzer.py
+│           ├── emotion_analyzer.py
+│           ├── filler_detector.py
+│           ├── metrics_builder.py
+│           └── json_exporter.py
+├── tests/
+├── examples/
+├── pyproject.toml
+└── README.md
+```
+
+---
+
+## 🤝 Contributing
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/amazing-feature`)
+3. Commit your changes (`git commit -m 'Add amazing feature'`)
+4. Push to the branch (`git push origin feature/amazing-feature`)
+5. Open a Pull Request
+
+---
+
+## 📝 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+---
+
+## 🙏 Acknowledgments
+
+- [OpenAI Whisper](https://github.com/openai/whisper) - Speech-to-text
+- [Silero VAD](https://github.com/snakers4/silero-vad) - Voice activity detection
+- [Librosa](https://librosa.org/) - Audio analysis
+- [SpeechBrain](https://speechbrain.github.io/) - Emotion recognition
+
+---
+
+## 📞 Support
+
+- **Issues**: [GitHub Issues](https://github.com/i-whimsy/audio-metrics-cli/issues)
+- **Discussions**: [GitHub Discussions](https://github.com/i-whimsy/audio-metrics-cli/discussions)
+- **Email**: clawbot@openclaw.ai
+
+---
+
+**Built with ❤️ by OpenClaw Team**

audio_metrics_cli-0.1.0/README.md

@@ -0,0 +1,253 @@
+# Audio Metrics CLI
+
+🎙️ **Cross-platform audio analysis toolkit for speech metrics extraction**
+
+[![PyPI version](https://badge.fury.io/py/audio-metrics-cli.svg)](https://badge.fury.io/py/audio-metrics-cli)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+---
+
+## 🚀 Quick Start
+
+### Installation
+
+```bash
+# Install from PyPI (recommended)
+pip install audio-metrics-cli
+
+# Or install from source (development)
+git clone https://github.com/i-whimsy/audio-metrics-cli.git
+cd audio-metrics-cli
+pip install -e ".[dev]"
+```
+
+### Basic Usage
+
+```bash
+# Analyze audio file
+audio-metrics analyze your_audio.wav --output result.json
+
+# With verbose output
+audio-metrics analyze audio.mp3 --verbose --show-progress
+
+# Transcribe only
+audio-metrics transcribe audio.m4a -o transcript.txt
+
+# Compare two audio files
+audio-metrics compare v1.wav v2.wav
+```
+
+---
+
+## 📦 Features
+
+### Core Metrics
+
+- **🎵 Audio Information**: Duration, sample rate, file size
+- **🗣️ Voice Activity Detection**: Speech/silence segmentation
+- **📝 Speech-to-Text**: Whisper-powered transcription
+- **🎼 Prosody Analysis**: Pitch, energy, speech rate
+- **😊 Emotion Recognition**: Emotional state detection (optional)
+- **🔤 Filler Word Detection**: "um", "uh", "like" detection
+
+### Supported Formats
+
+- ✅ WAV
+- ✅ MP3
+- ✅ M4A
+- ✅ FLAC
+- ✅ OGG
+
+### Cross-Platform
+
+- ✅ Windows
+- ✅ macOS
+- ✅ Linux
+
+---
+
+## 📖 Documentation
+
+### Command Line Interface
+
+#### `analyze` - Full Analysis
+
+```bash
+audio-metrics analyze audio.wav [OPTIONS]
+
+Options:
+  -o, --output PATH        Output JSON file path
+  -c, --config PATH        Configuration file
+  -m, --model TEXT         Whisper model (tiny/base/small/medium/large)
+  --no-emotion            Skip emotion analysis
+  --show-progress         Show progress bars
+  -v, --verbose           Verbose output
+  --help                  Show this message
+```
+
+#### `transcribe` - Speech to Text
+
+```bash
+audio-metrics transcribe audio.wav [OPTIONS]
+
+Options:
+  -o, --output PATH       Output transcript file
+  -m, --model TEXT        Whisper model
+  --language TEXT         Language code
+  --help                  Show this message
+```
+
+#### `compare` - Compare Audio Files
+
+```bash
+audio-metrics compare audio1.wav audio2.wav [OPTIONS]
+
+Options:
+  --format TEXT          Output format (text/json/markdown)
+  --help                 Show this message
+```
+
+---
+
+## 📊 Output Example
+
+```json
+{
+  "audio_info": {
+    "duration_seconds": 185.2,
+    "sample_rate": 44100,
+    "file_size_mb": 2.8
+  },
+  "vad_analysis": {
+    "speech_ratio": 0.81,
+    "pause_count": 23,
+    "avg_pause_duration": 1.1
+  },
+  "speech_metrics": {
+    "words_total": 820,
+    "words_per_minute": 266
+  },
+  "prosody_metrics": {
+    "pitch_mean_hz": 145.3,
+    "energy_cv": 0.33
+  },
+  "filler_metrics": {
+    "filler_word_count": 18,
+    "fillers_per_100_words": 2.2
+  }
+}
+```
+
+---
+
+## 🔧 Configuration
+
+Create a `config.json` file:
+
+```json
+{
+  "models": {
+    "speech_to_text": {
+      "provider": "whisper",
+      "model": "base",
+      "device": "auto"
+    },
+    "vad": {
+      "provider": "silero",
+      "threshold": 0.5
+    }
+  },
+  "audio_analysis": {
+    "enable_pitch": true,
+    "enable_energy": true,
+    "enable_pause": true
+  },
+  "features": {
+    "enable_emotion": true,
+    "skip_if_too_long": 3600
+  }
+}
+```
+
+---
+
+## 💻 Development
+
+### Setup Development Environment
+
+```bash
+# Clone repository
+git clone https://github.com/i-whimsy/audio-metrics-cli.git
+cd audio-metrics-cli
+
+# Install with dev dependencies
+pip install -e ".[dev]"
+
+# Run tests
+pytest tests/
+
+# Format code
+black src/
+ruff check src/
+```
+
+### Project Structure
+
+```
+audio-metrics-cli/
+├── src/
+│   └── audio_metrics/
+│       ├── cli.py              # CLI entry point
+│       ├── config.py           # Configuration
+│       └── modules/            # Core modules
+│           ├── audio_loader.py
+│           ├── vad_analyzer.py
+│           ├── speech_to_text.py
+│           ├── prosody_analyzer.py
+│           ├── emotion_analyzer.py
+│           ├── filler_detector.py
+│           ├── metrics_builder.py
+│           └── json_exporter.py
+├── tests/
+├── examples/
+├── pyproject.toml
+└── README.md
+```
+
+---
+
+## 🤝 Contributing
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/amazing-feature`)
+3. Commit your changes (`git commit -m 'Add amazing feature'`)
+4. Push to the branch (`git push origin feature/amazing-feature`)
+5. Open a Pull Request
+
+---
+
+## 📝 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+---
+
+## 🙏 Acknowledgments
+
+- [OpenAI Whisper](https://github.com/openai/whisper) - Speech-to-text
+- [Silero VAD](https://github.com/snakers4/silero-vad) - Voice activity detection
+- [Librosa](https://librosa.org/) - Audio analysis
+- [SpeechBrain](https://speechbrain.github.io/) - Emotion recognition
+
+---
+
+## 📞 Support
+
+- **Issues**: [GitHub Issues](https://github.com/i-whimsy/audio-metrics-cli/issues)
+- **Discussions**: [GitHub Discussions](https://github.com/i-whimsy/audio-metrics-cli/discussions)
+- **Email**: clawbot@openclaw.ai
+
+---
+
+**Built with ❤️ by OpenClaw Team**

audio_metrics_cli-0.1.0/pyproject.toml

@@ -0,0 +1,88 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "audio-metrics-cli"
+version = "0.1.0"
+description = "Cross-platform audio analysis toolkit for speech metrics extraction"
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.8"
+authors = [
+    {name = "OpenClaw", email = "clawbot@openclaw.ai"}
+]
+keywords = [
+    "audio",
+    "speech",
+    "analysis",
+    "metrics",
+    "whisper",
+    "vad",
+    "prosody",
+    "cli"
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Multimedia :: Sound/Audio :: Analysis",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+]
+
+dependencies = [
+    "numpy>=1.23.0",
+    "librosa>=0.10.0",
+    "soundfile>=0.12.0",
+    "openai-whisper>=20230314",
+    "click>=8.1.0",
+    "tqdm>=4.65.0",
+    "pydantic>=2.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-cov>=4.0.0",
+    "black>=23.0.0",
+    "ruff>=0.1.0",
+]
+emotion = [
+    "torch>=2.0.0",
+    "torchaudio>=2.0.0",
+    "speechbrain>=0.5.14",
+]
+
+[project.urls]
+Homepage = "https://github.com/i-whimsy/audio-metrics-cli"
+Repository = "https://github.com/i-whimsy/audio-metrics-cli.git"
+Documentation = "https://github.com/i-whimsy/audio-metrics-cli#readme"
+
+[project.scripts]
+audio-metrics = "audio_metrics.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+audio_metrics = ["*.json", "*.txt"]
+
+[tool.black]
+line-length = 100
+target-version = ['py38', 'py39', 'py310', 'py311', 'py312']
+
+[tool.ruff]
+line-length = 100
+target-version = "py38"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = "test_*.py"
+python_functions = "test_*"

audio_metrics_cli-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

audio_metrics_cli-0.1.0/src/audio_metrics/__init__.py

@@ -0,0 +1,14 @@
+"""
+Audio Metrics CLI - Cross-platform audio analysis toolkit
+
+Extract objective speech metrics from audio files.
+Output structured JSON for further analysis.
+"""
+
+__version__ = "0.1.0"
+__author__ = "OpenClaw"
+__email__ = "clawbot@openclaw.ai"
+
+from .cli import main
+
+__all__ = ["main"]