MEAD Audio
Project description
audio8
API examples using 8-mile 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)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mead-audio8-0.0.6.tar.gz
(32.7 kB
view hashes)
Built Distribution
Close
Hashes for mead_audio8-0.0.6-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a30263df29918dce7bad449d0aef6a9c09506a758580ca47ce29d890aa73d31a |
|
MD5 | 0e4525d49415a0179212bc0efe060650 |
|
BLAKE2b-256 | 131b5292b4a38d5a65a6295b777ba218a84ac4347eed94a79132df2b245da70e |