English to Katakana Translator

e2k is a Python library that translates English to Katakana using lightweight RNN models trained on data from Wiktionary and JMdict/EDICT. It only requires numpy as a runtime dependency. A Rust port with the same models and outputs lives in e2k-rs.

We also provide pretrained models and dictionaries in the Releases section (not included in the PyPI package).

Installation

pip install e2k

Usage

1. Basic Translation

Two models are available:

from e2k import P2K, C2K
from g2p_en import G2p # any g2p library with CMUdict phonemes can work

p2k = P2K()
g2p = G2p()

word = "geogaddi"
print(p2k(g2p(word)))  # ジオダギ

c2k = C2K()
print(c2k(word))       # ジオガディ

c2k(word, "top_p", p=0.9, t=2)
c2k(word, "top_k", k=5, seed=42)

Both models also come in a turbo variant, a smaller model distilled from the default one. It's about twice as fast with comparable accuracy, though its outputs differ on some words.

c2k = C2K(model="turbo")
p2k = P2K(model="turbo")

2. Pitch Accent Prediction

The library includes an RNN-based pitch accent predictor trained on Unidic.

from e2k import AccentPredictor as Ap, C2K

ap = Ap()
c2k = C2K()

word = "geogaddi"
katakana = c2k(word)
accent = ap(katakana)

print(f"Katakana: {katakana}, Accent: {accent}")
# Katakana: ジオガディ, Accent: 3

3. Pronunciation Validity (N-Gram Model)

You can check if a word should be transliterated or spelled as-is. A linear SVM over character n-gram scores decides, trained on CMUdict words against synthetic acronyms, abbreviations and random strings.

from e2k import NGram
ngram = NGram()

word = "ussr"
if ngram(word):
    print(c2k(word))
else:
    print(ngram.as_is(word))

Example output:

• ussr → ユーエスエスアール
• doggy → ドギー

4. Input/Output Symbol Tables

c2k.in_table  # valid characters
p2k.in_table  # valid phonemes
c2k.out_table # katakana output symbols
p2k.out_table # katakana output symbols
accent.in_table # valid katakana symbols for accent prediction

Performance

Develop

Dependencies

We use uv for dependency management:

• Root package (e2k in src/) is the PyPI library and only depends on numpy.
• Training code lives in the e2k_train/ workspace member (e2k_train) and carries the heavy ML/tooling dependencies.

For root package:

uv sync

Testing

The model files are tracked in git under src/e2k/models, so a fresh clone runs as is.

# test
uv run src/inference.py

Training

See here for instructions related to data preparation, training, evaluation and exporting.

License

• Code: Unlicense
• Dictionaries: CC-BY-SA (Wiktionary, JMdict/EDICT)
• Accent Predictor: Unidic (GPLv2.0/LGPLv2.1/BSD)
• N-Gram Model: CMUDict (BSD 2-Clause)

Machine learning weights may be considered derivative works, check the upstream licenses when distributing.

Credits

• Wiktionary
• JMdict / EDICT
• Unidic
• CMUDict