Repositories list

• PolyglotDB

  Public
  PolyglotDB is a package for phonetic corpus storage and analysis

  databaseinfluxdbneo4j+ 4

  databaseinfluxdbneo4jrest-apispeech-processingacousticsspeech-analysis

  Python

  •

  MIT License

  •1717 forks•5252 stars•4848 issues•22 pull requests•Updated Oct 8, 2026Oct 8, 2026

• Montreal-Forced-Aligner

  Public
  Command line utility for forced alignment using Kaldi

  pythonkaldipronunciation-dictionary+ 3

  pythonkaldipronunciation-dictionaryforced-alignmentgrapheme-to-phoneacoustic-model

  Python

  •

  MIT License

  •290290 forks•1.9k1.9k stars•284284 issues•55 pull requests•Updated Oct 8, 2026Oct 8, 2026

• kalpy

  Public
  Pybind11 bindings for Kaldi

  Jupyter Notebook

  •

  MIT License

  •33 forks•1515 stars•22 issues•00 pull requests•Updated Oct 8, 2026Oct 8, 2026

• mfa-interspeech2026

  Public
  Scripts for the Interspeech 2026 MFA paper

  Python

  •

  MIT License

  •00 forks•88 stars•00 issues•00 pull requests•Updated Sep 22, 2026Sep 22, 2026

• spade-audiobnc

  Public
  Scripts and pipeline for determining a usable subset of the AudioBNC corpus

  Python

  •00 forks•00 stars•00 issues•00 pull requests•Updated Jul 18, 2026Jul 18, 2026

• mfa-models

  Public
  Collection of pretrained models for the Montreal Forced Aligner

  Python

  •

  Creative Commons Attribution 4.0 International

  •2626 forks•199199 stars•2727 issues•00 pull requests•Updated Jul 8, 2026Jul 8, 2026

• MMO_vowel_overlap

  Public
  Multivariate modeled overlap: a method for measuring vowel merger

  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Apr 3, 2026Apr 3, 2026

• Anchor-annotator

  Public
  Anchor annotator is a program for inspecting corpora for the Montreal Forced Aligner and correcting transcriptions and pronunciations

  Python

  •

  MIT License

  •11 fork•66 stars•22 issues•00 pull requests•Updated Oct 12, 2025Oct 12, 2025

• mandarin-thchs-30-demo

  Public
  Demo corpus for THCHS-30

  Apache License 2.0

  •00 forks•00 stars•00 issues•00 pull requests•Updated Sep 24, 2025Sep 24, 2025

• japanese-jvs-demo

  Public
  Demo corpus for JVS

  Creative Commons Attribution Share Alike 4.0 International

  •00 forks•00 stars•00 issues•00 pull requests•Updated Sep 24, 2025Sep 24, 2025

• librispeech-demo

  Public
  Demo corpus for librispeech

  MIT License

  •00 forks•00 stars•00 issues•00 pull requests•Updated Sep 22, 2025Sep 22, 2025

• aligned-librispeech

  Public
  Aligned version of LibriSpeech test-clean for use in benchmarking English forced alignment

  00 forks•11 star•00 issues•00 pull requests•Updated Sep 14, 2025Sep 14, 2025

• polyglotdb-docker

  Public
  00 forks•00 stars•00 issues•00 pull requests•Updated Jul 14, 2025Jul 14, 2025

• SPADE

  Public
  Anything SPADE-related not covered in another repository, including scripts for analyzing SPADE datasets using PolyglotDB.

  R

  •

  MIT License

  •44 forks•11 star•44 issues•11 pull request•Updated Dec 27, 2022Dec 27, 2022

• ISCAN

  Public
  Development repository for Integrated Speech Corpus Analaysis (ISCAN)

  JavaScript

  •

  MIT License

  •00 forks•1010 stars•3333 issues•22 pull requests•Updated Jul 15, 2022Jul 15, 2022

• iscan-spade-server

  Public
  Django server set up for the SPADE project

  Python

  •

  MIT License

  •00 forks•11 star•11 issue•11 pull request•Updated Jan 6, 2022Jan 6, 2022

• montrealcorpustools.github.io

  Public
  00 forks•00 stars•00 issues•00 pull requests•Updated Oct 12, 2021Oct 12, 2021

• Phonetisaurus

  Public
  Phonetisaurus G2P

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •129129 forks•22 stars•00 issues•00 pull requests•Updated Jun 22, 2021Jun 22, 2021

• opengrm-ngram

  Public
  Read-only unofficial mirror of the OpenGrm NGram Library

  C++

  •

  Other

  •33 forks•00 stars•00 issues•00 pull requests•Updated Jun 22, 2021Jun 22, 2021

• benchmarking

  Public
  Bencharking suites for PolyglotDB

  Python

  •

  MIT License

  •22 forks•00 stars•00 issues•11 pull request•Updated Jun 22, 2021Jun 22, 2021

• sct_resources

  Public
  resources for SCT (this should be made private)

  Python

  •33 forks•00 stars•00 issues•00 pull requests•Updated Jun 22, 2021Jun 22, 2021

• mfa_test_data

  Public
  Test datasets for the Montreal Forced Aligner

  00 forks•11 star•00 issues•00 pull requests•Updated Jun 22, 2021Jun 22, 2021

• speechcorpustools

  Public
  Easier analysis of large speech corpora

  Python

  •88 forks•2525 stars•55 issues•00 pull requests•Updated Jun 22, 2021Jun 22, 2021

• kaldi

  Public
  This is now the official location of the Kaldi project.

  Shell

  •

  Other

  •5.4k5.4k forks•11 star•00 issues•00 pull requests•Updated Jun 22, 2021Jun 22, 2021

• MFA-reorganization-scripts

  Public
  Collection of scripts and utilities for reorganizing corpora to use with the Montreal Forced Aligner

  Python

  •

  MIT License

  •66 forks•4343 stars•11 issue•00 pull requests•Updated Jun 22, 2021Jun 22, 2021