A python-port of julius-speech/segmentation-kit
Project description
PySegmentKit
A python-port of julius-speech/segmentation-kit
- No more Perl
- No more edit original script to set options
Usage
from PySegmentKit import PySegmentKit, PSKError
sk = PySegmentKit(input(),
disable_silence_at_ends=False,
leave_dict=False,
debug=False,
triphone=False,
input_mfcc=False)
try:
segmented = sk.segment()
for result in segmented.keys():
print("=====Segmentation result of {}.wav=====".format(result))
for begintime, endtime, unit in segmented[result]:
print("{:.7f} {:.7f} {}".format(begintime, endtime, unit))
except PSKError as e:
print(e)
Install as a third-party library
- PyPI
$ pip install PySegmentKit
Use as a CLI
- Copy
$ git clone https://github.com/urushiyama/PySegmentKit.git
$ python PySegmentKit/main.py -h # show detailed usage
License
This library is released under MIT License.
The original perl script, julius-speech/segmentation-kit, is released under MIT License.
This library bundles some binaries of Julius, which is released under BSD 3-Clause "New" or "Revised" License.
Please refer to ACKNOWLEDGEMENTS.md for detail.
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
PySegmentKit-0.2.1.tar.gz
(3.7 MB
view hashes)
Built Distribution
Close
Hashes for PySegmentKit-0.2.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8c448d77cf309258af3b95517d021ade14ebb41d841c4bd3fb3444c63520aa50 |
|
MD5 | d35faa3d656d9788f5cdbd534cf0c927 |
|
BLAKE2b-256 | 1899dcb067b7569c5c5b17151fe8388c1ea658b333beb506684d579b6fa1d7c5 |