cadia-lvl/kaldi-speaker-diarization cadia-lvl/kaldi-speaker-diarization

  • Stars
    star
    13
  • Rank 1,512,713 (Top 30 %)
  • Language
    Shell
  • License
    Apache License 2.0
  • Created almost 5 years ago
  • Updated 4 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
cadia-lvl/kaldi-speaker-diarization
github

cadia-lvl

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This repository creates speaker diarization recipes to be used within the egs folder of kaldi.

More Repositories

1

punctuation-prediction

Support tools for punctuation and boundary detection for ASR output.
Python
57
star
2

icelandic-NLP-resources

Overview of Icelandic NLP resources at a glance
15
star
3

ice-asr

An automatic speech recognition environment for Icelandic based on Kaldi
Python
13
star
4

ss_asr

A semi-supervised sequence-to-sequence ASR
Python
8
star
5

samromur-asr

Automatic Speech Recognition (ASR) system for the Samrómur speech corpus using Kaldi
Shell
6
star
6

ictk

📚 Icelandic Corpora Toolkit - A collection of scripts to use with various Icelandic text corpora
Python
5
star
7

WebRICE

WebRICE (Web Reader ICE) is an open source web reader in development at Reykjavik University.
TypeScript
5
star
8

regina_normalizer

Python
4
star
9

LOBE

LOBE is a recording client made specifically for TTS data collections. It supports multiple collections, single and multi-speaker, and can prompt sentences based on phonetic coverage.
Python
4
star
10

tacotron

E2E-NN-TTS
Python
3
star
11

NER

Named entity recognition for Icelandic
Python
3
star
12

unit-selection-festival

First version of Unit Selection recipe for Icelandic from Reykjavík University
Shell
3
star
13

Icelandic-textnorm

Text normalization for Icelandic
Python
2
star
14

speech-corpora-toolkit

A collection of tools for processing public domain audio and scripts to prepare them for segmentation and alignment.
Python
2
star
15

deCODE

Voice Source and Vocal tract features
Shell
2
star
16

samromur

TypeScript
2
star
17

POS

A part-of-speech tagger, tailored to Icelandic
Python
2
star
18

MOSI

TTS evaluation platform
Jinja
2
star
19

sentiment-analysis

Deep Learning and Machine learning training on Icelandic translated data
Jupyter Notebook
2
star
20

althingi-asr

An ASR recipe and speech corpus of Icelandic parliamentary speeches
Shell
2
star
21

broadcast_data_prep

This repository has scripts to extract data from various sources for ASR and speaker diarization.
Python
1
star
22

lm-is-forms

Generate language model data for form fillables
Python
1
star
23

RUQuAD

A repository with information about Reykjavik University Question-Answer Dataset
1
star
24

qa-crowdsourcing-api

TypeScript
1
star
25

BinPackageAPI

Python
1
star
26

metawave

Meta-information tool for TTS datasets
Python
1
star
27

samromur-mfa

Aligner with MFA for Samromur dataset
Shell
1
star
28

compute

LVL Computing Resources
1
star
29

tal.ru.is

Vefgátt fyrir íslenskan talgreini
Python
1
star
30

GreynirCorrectAPI

Python
1
star
31

ebs

Epoch Based Spectrum Estimation for Speech
MATLAB
1
star
32

diar-az

Diarization A to Z - Kaldi to Gecko to Kaldi and corpus and back
Python
1
star
33

samromur-chat

Samrómur chat is a VoIP web application written in Typescript.
TypeScript
1
star
34

SoftwareDevelopmentGuidelines

The LVL software development guidelines
1
star
35

cadia-lvl.github.io

This is the Language and Voice Lab's GitHub landing page
HTML
1
star
36

Greynir-setningafraedi

Rannsóknarverkefni í grunnnámi í Tölvunarfræði við HR. Greynir tólið nýtt til að búa til frumgerð af kennsluforriti fyrir framhaldsskólanema.
HTML
1
star
37

alignment-and-segmentation

Scripts for preparing the RUV TV and radio material for ASR
Shell
1
star