doheejin/HiPAMA
This repository is the implementation of the HiPAMA architecture, introduced in the paper, Hierarchical Pronunciation Assessment with Multi-Aspect Attention (ICASSP 2023).
This project helps speech technologists and language educators evaluate spoken pronunciation. You provide an audio recording of someone speaking and the expected text, and it assesses pronunciation quality at different levels (like individual sounds and whole words). It's designed for researchers and practitioners focused on speech technology and language learning.
No commits in the last 6 months.
Use this if you need to automatically assess and provide feedback on the pronunciation of non-native speakers or in language learning applications.
Not ideal if you need a general-purpose speech-to-text transcriber or a tool for speaker identification.
Stars
38
Forks
2
Language
Python
License
BSD-3-Clause
Category
Last pushed
Apr 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/doheejin/HiPAMA"
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