CLI to create a pronunciation dictionary by predicting English ARPAbet phonemes using seq2seq model from g2pE and the possibility of ignoring punctuation and splitting on hyphens before prediction.
Project description
dict-from-g2pE
CLI to create a pronunciation dictionary by predicting English ARPAbet phonemes using seq2seq model from g2pE and the possibility of ignoring punctuation and splitting on hyphens before prediction.
Installation
pip install dict-from-g2pE --user
Usage
dict-from-g2pE-cli
Example
# Create example vocabulary
cat > /tmp/vocabulary.txt << EOF
Test?
abc,
"def
Test-def.
"xyz?
"uv-w?
EOF
# Create dictionary from vocabulary and example dictionary
dict-from-g2pE-cli \
/tmp/vocabulary.txt \
/tmp/result.dict \
--split-on-hyphen \
--n-jobs 4
cat /tmp/result.dict
# -------
# Output:
# -------
# Test? T EH1 S T ?
# abc, AE1 B K ,
# "def " D EH1 F
# Test-def. T EH1 S T - D EH1 F .
# "xyz? " Z IH1 JH IH0 Z ?
# "uv-w? " AH1 V - V IY1 ?
# -------
Acknowledgments
g2pE: A Simple Python Module for English Grapheme To Phoneme Conversion
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
dict-from-g2pE-0.0.1.tar.gz
(8.5 kB
view hashes)
Built Distribution
Close
Hashes for dict_from_g2pE-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 987c88a71ef1f6418067b8144244fe55f003d9f60fcb7db804e79a6ce54b3b2c |
|
MD5 | 8ff05e4adaeeb003d61d0c28f20c5a8e |
|
BLAKE2b-256 | dea6606766237954c7174e35dce35df2e13602fa62b395a898dfecb761be3b33 |