Metadata-Version: 2.1
Name: mead-audio8
Version: 0.0.6
Summary: MEAD Audio
Home-page: UNKNOWN
Author: dpressel
Author-email: dpressel@gmail.com
License: Apache 2.0
Keywords: deep-learning,audio,pytorch
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Description-Content-Type: text/markdown
Provides-Extra: test
Provides-Extra: scipy
Provides-Extra: ctcdecode

# audio8
API examples using [8-mile](https://github.com/dpressel/mead-baseline) for audio

## Implementation

The codebase relies primarily on `8-mile` (`mead-layers`) for its modeling and optimization code.
Whats left is pretty much just training and inference code

## Dependencies

The code depends on:
  - `editdistance` (for error evaluation)
  - `numpy`
  - `six`
  - `soundfile`
  - `mead-baseline`
  - `pytorch`

There are a few optional dependencies
  - `scipy` (for on-the-fly resampling of wav files)
  - `ctcdecode` (for prefix beam decoding with optional LM)


