IAMAI ASR Post Process Library
Project description
nlp-text-corrector is a python package that helps post process the raw ASR output
Parsing of numbers expressed as words in English and convert them to integer values.
Detection of ordinal, cardinal and decimal numbers in a stream of Englishwords and get their decimal digit representations.
Detection of email/website addresses as words in English and convert them to proper email/website format.
Detection of times expressed as raw text in English to proper time format.
Compatibility
Tested on python 3.7. Requires Python >= 3.6.
License
This sofware is distributed under the MIT license of which you should have received a copy (see LICENSE file in this repository).
Installation
nlp-text-corrector does not depend on any other third party package.
To install nlp-text-corrector in your (virtual) environment:
pip install nlp-text-corrector
That’s all folks!
Usage examples
Parse and convert
Examples:
>>> from nlp_text_corrector import asr_post_process
>>> asr_post_process.convert("Book twenty first century marvel movie for my two kids of age nine and thirteen at eight twenty two pm tonight")
Book 21st century marvel movie for my 2 kids of age 9 and 13 at 8:22 pm tonight
>>> asr_post_process.convert("fifty-one million five hundred seventy-eight thousand three hundred two")
51578302
>>> asr_post_process.convert("eighty-one")
81
>>> asr_post_process.convert("On May twenty-third , I bought twenty-five cows, twelve chickens and one hundred twenty five point four zero kg of potatoes.")
On May 23rd, I bought 25 cows, 12 chickens and 125.40 kg of potatoes.
Contribute
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
Built Distribution
File details
Details for the file nlp_text_corrector-0.0.3.tar.gz
.
File metadata
- Download URL: nlp_text_corrector-0.0.3.tar.gz
- Upload date:
- Size: 4.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.7.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f9e4f0a1e4e1a1ab1908d20904c97812b852d4f520e73e1bebc5dc2d236a4d1b |
|
MD5 | 7bc9fc9d56f89fd804832ad1f3321efa |
|
BLAKE2b-256 | c0abdef33bd0f113a533b0c3775d11f39de14e4bba365c5d15c95dfc49e9ed30 |
File details
Details for the file nlp_text_corrector-0.0.3-py3-none-any.whl
.
File metadata
- Download URL: nlp_text_corrector-0.0.3-py3-none-any.whl
- Upload date:
- Size: 4.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.7.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c974f9dfa7130b4b2a17b165d70f3e0011fe9807a02436c5120c588636a9eec8 |
|
MD5 | 53eb5dd5ced9fa04b362edfca832c584 |
|
BLAKE2b-256 | 501f111bdc63d66c51cf843911ac88bcfde7a62d8f67343efdf1004dc8890a50 |