sea-g2p 0.5.0

Fast multilingual text-to-phoneme converter for South East Asian languages.

🦭 SEA-G2P

Fast multilingual text-to-phoneme converter for South East Asian languages.

Author: Pham Nguyen Ngoc Bao

Installation

pip install sea-g2p

Requires espeak-ng only for fallback (built-in dictionary already covers ~99.9% of words).

Usage

Simple Pipeline

from sea_g2p import SEAPipeline

pipeline = SEAPipeline(lang="vi")
result = pipeline.run("Giá SP500 hôm nay là 4.200,5 điểm.")
print(result)
#zˈaːɜ ˈɛɜt̪ pˈe nˈam tʃˈam hˈom nˈaj lˌaː2 bˈoɜn ŋˈi2n hˈaːj tʃˈam fˈəɪ4 nˈam ɗˈiɛ4m.

Individual Modules

from sea_g2p import Normalizer, G2P

normalizer = Normalizer(lang="vi")
g2p = G2P(lang="vi")

text = "Giá SP500 hôm nay là 4.200,5 điểm"
normalized = normalizer.normalize(text)
print(normalized)
phonemes = g2p.convert(normalized)
print(phonemes)
#giá ét pê năm trăm hôm nay là bốn nghìn hai trăm phẩy năm điểm.
#zˈaːɜ ˈɛɜt̪ pˈe nˈam tʃˈam hˈom nˈaj lˌaː2 bˈoɜn ŋˈi2n hˈaːj tʃˈam fˈəɪ4 nˈam ɗˈiɛ4m.

Features

• Fast dictionary-based lookup using SQLite.
• Vietnamese text normalization (numbers, dates, units).
• Bilingual support (Vietnamese/English).
• Batch processing for efficiency.
• eSpeak-NG fallback for unknown words.

Development

To install for development purposes:

1. Clone the repository:

   git clone https://github.com/pnnbao97/sea-g2p
   cd sea-g2p
   

2. Install in editable mode:

   pip install -e .