saarus72/text_normalization
T5-based (russian) text normalization
This project helps convert raw, informal Russian text into a more standardized format suitable for text-to-speech (TTS) systems. It takes everyday Russian sentences that might include numbers, abbreviations, or mixed-language terms (like 'iphone 10X') and converts them into their fully written-out, grammatically correct Russian equivalents. Anyone working with Russian speech synthesis, such as content creators, linguists, or educators, would find this useful.
No commits in the last 6 months.
Use this if you need to reliably transform casual, written Russian text into a clean, spoken-word-ready format for speech synthesis applications.
Not ideal if your primary need is for inverse text normalization (converting spoken numbers back to digits), although it includes components that assist with that.
Stars
26
Forks
2
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jan 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/saarus72/text_normalization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/langfun
OO for LLMs
tanaos/artifex
Small Language Model Inference, Fine-Tuning and Observability. No GPU, no labeled data needed.
preligens-lab/textnoisr
Adding random noise to a text dataset, and controlling very accurately the quality of the result
vulnerability-lookup/VulnTrain
A tool to generate datasets and models based on vulnerabilities descriptions from @Vulnerability-Lookup.
masakhane-io/masakhane-mt
Machine Translation for Africa