2 projects
wordninja-pp
Probabilistically split concatenated words across 90 languages — incl. English, Spanish, French, German, Italian, Portuguese, Russian, Hebrew, Chinese, Japanese, Korean, Vietnamese, Arabic, Hindi, Bengali, Tamil, Telugu, Thai, Greek, Turkish, Polish, Dutch, Swedish, Norwegian, Finnish, Marathi, Punjabi, Gujarati, Kannada, Burmese, Swahili, Amharic, Welsh, Breton, Mongolian and 50+ more
syllable-counter
Multi-language syllable counter and TTS duration estimator (12 languages)