peresolb Goto Github PK

aeneas

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

artificial-intelligence-norway

Artificial Intelligence in Norway

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

dep_search

Search back-end for dependency tree search. See the docs at https://fginter.github.io/dep_search/

forced_alignment_stortinget

formvariasjon

statistikk over formvariasjon i Ordbanken

g2p-no

Grapheme-to-Phoneme models for Norwegian

nltk_contrib

NLTK Contrib

number-conversion

This repo contains scripts that converts numbers written as digits to numbers written with Norwegian words, and conversely, from numbers written as Norwegian words to digits.

parlaspeech-no

Code for bootstrapping ASR datasets from parliamentary recordings and transcripts

preprocess-asr

Automatically improve ASR transcriptions using manually written records

sampa_to_ipa

Script for converting transcriptions in the X-SAMPA conventions of the Norwegian NST pronunciation lexicon to IPA

scribe-project.github.io

SCRIBE project public web pages

test_classifier

transcribe_w2v

Transcribe large audiofiles with wav2vec2

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

w2v_notebook