soundhub-utils 0.0.2__tar.gz

soundhub_utils-0.0.2/LICENSE.md

@@ -0,0 +1,28 @@
+BSD 3-Clause License
+
+Copyright (c) 2025, Regents of the University of California (Schmidt Center for Data Science and Environment at UC Berkeley)
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

soundhub_utils-0.0.2/PKG-INFO

@@ -0,0 +1,138 @@
+Metadata-Version: 2.4
+Name: soundhub_utils
+Version: 0.0.2
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+Requires-Dist: tf_keras
+Requires-Dist: cocina
+Requires-Dist: sox_tensorflow
+Dynamic: license-file
+
+# Soundhub Utils
+
+Audio processing utilities library for SoundHub model integration. This package provides core functionality for:
+
+1. Reading audio files from AWS S3, Google Cloud Storage, HTTPS URLs, and local filesystems
+2. Standard audio preprocessing (resampling, segmentation, format conversion)
+3. Spectrogram generation using multiple backends (TensorFlow, PyTorch, librosa)
+4. Unified I/O interface across different storage platforms
+
+**Note**: This is a utilities library. For running models (like OWL), see [`soundhub_model_runner`](https://github.com/your-org/soundhub_model_runner).
+
+## Table of Contents
+
+- [Installation](#installation)
+- [Core Modules](#core-modules)
+- [Usage Examples](#usage-examples)
+- [Style Guide](#style-guide)
+
+---
+
+## Installation
+
+### Using Pixi (Recommended for Development)
+
+Requirements are managed through [Pixi](https://pixi.sh/latest). Install pixi, then:
+
+```bash
+# Run commands in the pixi environment
+pixi run python -c "import soundhub_utils; print(soundhub_utils.__version__)"
+
+# Launch jupyter for development
+pixi run jupyter lab .
+```
+
+The `pyproject.toml` includes `soundhub_utils = { path = ".", editable = true }`, so no separate installation is needed.
+
+### Using pip
+
+```bash
+# Install from local directory
+pip install -e .
+
+# Or install specific version (when published to PyPI)
+pip install soundhub-utils
+```
+
+---
+
+## Core Modules
+
+### I/O (soundhub_utils.io)
+
+Unified interface for reading/writing audio files across multiple storage platforms:
+
+- **`soundhub_utils.io.aws`**: AWS S3 integration with partial FLAC download support
+- **`soundhub_utils.io.gcs`**: Google Cloud Storage operations
+- **`soundhub_utils.io.local`**: Local filesystem operations
+- **`soundhub_utils.io.url`**: HTTP/HTTPS streaming and downloads
+- **`soundhub_utils.io.io`**: Unified interface that auto-routes based on URI scheme
+
+### Audio Processing (soundhub_utils.audio)
+
+Audio processing backends for spectrogram generation and preprocessing:
+
+- **`soundhub_utils.audio.tensorflow_audio`**: TensorFlow-native audio processing
+
+### Utilities (soundhub_utils.utils)
+
+Helper functions for audio processing:
+
+- **`soundhub_utils.utils.audio`**: Format conversion and validation
+- **`soundhub_utils.utils.flac`**: FLAC metadata extraction and time-range processing
+- **`soundhub_utils.names`**: File naming conventions for audio and spectrograms
+
+---
+
+## Usage Examples
+
+### Reading Audio from Different Sources
+
+```python
+from soundhub_utils.io import io
+
+# Read from S3
+audio_data = io.read_flac("s3://bucket/path/audio.flac")
+
+# Read from Google Cloud Storage
+audio_data = io.read_flac("gs://bucket/path/audio.flac")
+
+# Read from HTTPS URL
+audio_data = io.read_flac("https://example.com/audio.flac")
+
+# Read from local file
+audio_data = io.read_flac("/path/to/audio.flac")
+
+# Read partial FLAC (time range)
+audio_data = io.read_partial_flac(
+    "s3://bucket/audio.flac",
+    start_time=10.0,  # seconds
+    duration=30.0      # seconds
+)
+```
+
+### Generating Spectrograms
+
+```python
+from soundhub_utils.audio import tensorflow_audio
+
+# Generate spectrograms from audio file
+spectrograms = tensorflow_audio.generate_spectrograms(
+    audio_path="/path/to/audio.flac",
+    sample_rate=8000,
+    segment_duration=12.0,
+    spectrogram_shape=[257, 1000]
+)
+```
+
+---
+
+## Style Guide
+
+Following PEP8. See [setup.cfg](./setup.cfg) for exceptions. Use `pycodestyle .` to check compliance.
+
+---
+
+## License
+
+BSD 3-Clause

soundhub_utils-0.0.2/README.md

@@ -0,0 +1,128 @@
+# Soundhub Utils
+
+Audio processing utilities library for SoundHub model integration. This package provides core functionality for:
+
+1. Reading audio files from AWS S3, Google Cloud Storage, HTTPS URLs, and local filesystems
+2. Standard audio preprocessing (resampling, segmentation, format conversion)
+3. Spectrogram generation using multiple backends (TensorFlow, PyTorch, librosa)
+4. Unified I/O interface across different storage platforms
+
+**Note**: This is a utilities library. For running models (like OWL), see [`soundhub_model_runner`](https://github.com/your-org/soundhub_model_runner).
+
+## Table of Contents
+
+- [Installation](#installation)
+- [Core Modules](#core-modules)
+- [Usage Examples](#usage-examples)
+- [Style Guide](#style-guide)
+
+---
+
+## Installation
+
+### Using Pixi (Recommended for Development)
+
+Requirements are managed through [Pixi](https://pixi.sh/latest). Install pixi, then:
+
+```bash
+# Run commands in the pixi environment
+pixi run python -c "import soundhub_utils; print(soundhub_utils.__version__)"
+
+# Launch jupyter for development
+pixi run jupyter lab .
+```
+
+The `pyproject.toml` includes `soundhub_utils = { path = ".", editable = true }`, so no separate installation is needed.
+
+### Using pip
+
+```bash
+# Install from local directory
+pip install -e .
+
+# Or install specific version (when published to PyPI)
+pip install soundhub-utils
+```
+
+---
+
+## Core Modules
+
+### I/O (soundhub_utils.io)
+
+Unified interface for reading/writing audio files across multiple storage platforms:
+
+- **`soundhub_utils.io.aws`**: AWS S3 integration with partial FLAC download support
+- **`soundhub_utils.io.gcs`**: Google Cloud Storage operations
+- **`soundhub_utils.io.local`**: Local filesystem operations
+- **`soundhub_utils.io.url`**: HTTP/HTTPS streaming and downloads
+- **`soundhub_utils.io.io`**: Unified interface that auto-routes based on URI scheme
+
+### Audio Processing (soundhub_utils.audio)
+
+Audio processing backends for spectrogram generation and preprocessing:
+
+- **`soundhub_utils.audio.tensorflow_audio`**: TensorFlow-native audio processing
+
+### Utilities (soundhub_utils.utils)
+
+Helper functions for audio processing:
+
+- **`soundhub_utils.utils.audio`**: Format conversion and validation
+- **`soundhub_utils.utils.flac`**: FLAC metadata extraction and time-range processing
+- **`soundhub_utils.names`**: File naming conventions for audio and spectrograms
+
+---
+
+## Usage Examples
+
+### Reading Audio from Different Sources
+
+```python
+from soundhub_utils.io import io
+
+# Read from S3
+audio_data = io.read_flac("s3://bucket/path/audio.flac")
+
+# Read from Google Cloud Storage
+audio_data = io.read_flac("gs://bucket/path/audio.flac")
+
+# Read from HTTPS URL
+audio_data = io.read_flac("https://example.com/audio.flac")
+
+# Read from local file
+audio_data = io.read_flac("/path/to/audio.flac")
+
+# Read partial FLAC (time range)
+audio_data = io.read_partial_flac(
+    "s3://bucket/audio.flac",
+    start_time=10.0,  # seconds
+    duration=30.0      # seconds
+)
+```
+
+### Generating Spectrograms
+
+```python
+from soundhub_utils.audio import tensorflow_audio
+
+# Generate spectrograms from audio file
+spectrograms = tensorflow_audio.generate_spectrograms(
+    audio_path="/path/to/audio.flac",
+    sample_rate=8000,
+    segment_duration=12.0,
+    spectrogram_shape=[257, 1000]
+)
+```
+
+---
+
+## Style Guide
+
+Following PEP8. See [setup.cfg](./setup.cfg) for exceptions. Use `pycodestyle .` to check compliance.
+
+---
+
+## License
+
+BSD 3-Clause

soundhub_utils-0.0.2/pyproject.toml

@@ -0,0 +1,66 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "soundhub_utils"
+version = "0.0.2"
+readme = "README.md"
+dependencies = [
+	'tf_keras',
+	'cocina',
+	'sox_tensorflow']
+
+[tool.setuptools]
+packages = { find = {} }  # Auto-discover all packages including subpackages
+
+[tool.pixi.project]
+channels = ["conda-forge", "pytorch"]
+platforms = ["osx-arm64", "linux-64", "osx-64", "linux-aarch64"]
+
+[tool.pixi.pypi-dependencies]
+soundhub_utils = { path = ".", editable = true }
+
+# Feature for local cocina development
+[tool.pixi.feature.local-cocina.pypi-dependencies]
+cocina = { path = "/Users/brookie/code/dse/cocina/cocina", editable = true }
+sox_tensorflow = { path = "/Users/brookie/code/dse/soundhub/sox_gpu/codebase/sox_tensorflow", editable = true }
+
+[tool.pixi.dependencies]
+pycodestyle = ">=2.14.0,<3"
+ipykernel = ">=7.1.0,<8"
+jupyterlab = ">=4.4.10,<5"
+numpy = ">=2.3.4,<3"
+pandas = ">=2.3.3,<3"
+pydub = ">=0.25.1,<0.26"
+boto3 = ">=1.40.65,<2"
+audioop-lts = ">=0.2.2,<0.3"
+pysoundfile = ">=0.13.1,<0.14"
+matplotlib = ">=3.10.7,<4"
+scipy = ">=1.16.3,<2"
+google-cloud-storage = ">=3.4.1,<4"
+librosa = ">=0.11.0,<0.12"
+typing_extensions = ">=4.15.0,<5"
+referencing = ">=0.37.0,<0.38"
+pillow = ">=12.0.0,<13"
+pyarrow = ">=19.0.1,<23"
+tensorflow = ">=2.18.0,<3"
+pytorch = ">=2.6.0,<3"
+torchaudio = ">=2.7.0,<3"
+duckdb = ">=1.4.1,<2"
+
+
+# Environments
+[tool.pixi.environments]
+default = { features = [] }
+local = { features = ["local-cocina"] }
+dev = { features = ["dev"] }
+
+[tool.pixi.feature.dev.dependencies]
+twine = "*"
+
+[tool.pixi.feature.dev.pypi-dependencies]
+build = "*"
+h5py = ">=3.15.1,<4"
+
+

soundhub_utils-0.0.2/setup.cfg

@@ -0,0 +1,8 @@
+[pycodestyle]
+max-line-length = 100
+ignore = E125,E128,E502,E731,E722,E402
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

soundhub_utils-0.0.2/soundhub_utils/__init__.py

@@ -0,0 +1,7 @@
+"""
+Soundhub Utils Module
+
+Core utilities for audio processing and model integration in soundhub
+
+License: BSD 3-Clause
+"""

soundhub_utils-0.0.2/soundhub_utils/audio/__init__.py

@@ -0,0 +1 @@
+# __init__.py