Skip to main content

The Unified Parser unifies Indian languages using a common label set and syllable structure. It converts text to a common label set, generates phoneme sequences and improves natural language understanding in Indian languages. The method requires basic language knowledge and can achieve more than 95% accuracy with good lexicons. New Indian language parsers can be easily developed using this unified approach.

Project description

Python_Unified_Parser

This parser attempts to unify the languages based on the Common Label Set. It is designed across all the languages capitalising on the syllable structure of Indian languages. The Unified Parser converts UTF-8 text to common label set, applies letter-to-sound rules and generates the corresponding phoneme sequences. The effort is a step towards natural language understanding system that operates on Indian languages and generates the parsed output. This structured method requires only knowledge of the basic language. With good lexicons it is possible to get more than 95% correctness of words in a language. This method can be further extended for a number of other Indian languages in minimal time and effort. Given the unity in the diversity of Indian languages, developing parsers for new languages is easy using the unified approach.

Our python parser - uparser.py - Combines lex and yacc functionality in a single python script using the PLY framework.

Publications

Baby, Arun, et al. "A unified parser for developing Indian language text to speech synthesizers." Text, Speech, and Dialogue: 19th International Conference, TSD 2016, Brno, Czech Republic, September 12-16, 2016, Proceedings 19. Springer International Publishing, 2016.

Installation

pip install indic_unified_parser

How to use

from indic_unified_parser import uparser
parsed_output_string = wordparse(<word : str>, <lsflag : int>, <wfflag : int>, <clearflag : int>)
  1. lsflag: always 0. Deprecated.
  2. wfflag: 0 for Monophone parsing, 1 for syllable parsing, 2 for Akshara Parsing"
  3. clearflag: 1 for removing the lisp like format of output and to just produce space separated output. Otherwise, 0.

Examples

URLS

Homepage

Authors

Vikram K V, Dual Degree, Computer Science Dept, IIT Madras.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

indic_unified_parser-1.0.5.tar.gz (40.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

indic_unified_parser-1.0.5-py3-none-any.whl (40.6 kB view details)

Uploaded Python 3

File details

Details for the file indic_unified_parser-1.0.5.tar.gz.

File metadata

  • Download URL: indic_unified_parser-1.0.5.tar.gz
  • Upload date:
  • Size: 40.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.10

File hashes

Hashes for indic_unified_parser-1.0.5.tar.gz
Algorithm Hash digest
SHA256 d68732364a295538aceb56c135b499fef25b689754e3bb26f7a9f46d16675209
MD5 7e289d8a67a6ee855cc55ca8a4165a3e
BLAKE2b-256 1677455ca2f00f50d6be2f47228d022e3eb1d66f85e44a40d0fec2a90337584f

See more details on using hashes here.

File details

Details for the file indic_unified_parser-1.0.5-py3-none-any.whl.

File metadata

File hashes

Hashes for indic_unified_parser-1.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 dab1ac077fa43cc395426808cc33e9983b27560b080cc0ac26c61aa13d43efc9
MD5 ef8d2d43ae7aebdc4090f36a377257c4
BLAKE2b-256 dd285898ff8aa34c94fd0a5dd0a5f827785d383805a5c56daa374f2700efc302

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page