vsiivola / variKN
A toolkit for producing n-gram language models. The highlights are the implementation of Kneser-Ney growing and revised Kneser pruning methods.
☆40Updated 5 months ago
Alternatives and similar repositories for variKN:
Users that are interested in variKN are comparing it to the libraries listed below
- SIGMORPHON 2020 Shared Task: Grapheme-to-Phoneme, Unsupervised Induction of Morphology, and Typologically Diverse Morphological Inflectio…☆35Updated 4 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 6 months ago
- Links to data used in Sproat & Jaitly (https://arxiv.org/abs/1611.00068) experiments.☆76Updated 3 years ago
- The Fisher and CALLHOME Spanish–English Speech Translation Corpus☆39Updated 3 years ago
- This repository contains data used in the NAACL 2021 Paper - Proteno: Text Normalization with Limited Data for Fast Deployment in Text to…☆43Updated 3 years ago
- readers that enable reading kaldi ark in tensorflow☆17Updated 6 years ago
- Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation☆16Updated 4 years ago
- RNNs for Text Normalization☆38Updated 7 years ago
- Properly handle position-dependent phones in a subword lexicon FST☆31Updated 4 years ago
- A bunch of scripts exploiting several tools to perform inverse text normalization (ITN)☆21Updated 7 years ago
- Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different language model☆34Updated 5 years ago
- ☆56Updated 2 years ago
- Python library for n-gram models in ARPA format☆40Updated 2 years ago
- Convert words to numbers☆20Updated 2 years ago
- Self-contained Python package for OpenFst☆51Updated 2 years ago
- Support tools for punctuation and boundary detection for ASR output.☆57Updated 2 years ago
- An adaptation of Fairseq to (End-to-end) speech translation.☆22Updated 2 years ago
- phone inventory library☆16Updated last year
- Large scale (>200h) and publicly available read audio book corpus. This corpus is an augmentation of LibriSpeech ASR Corpus (1000h) and c…☆43Updated 2 years ago
- ☆34Updated 5 months ago
- A phoneme-allophone database for many languages☆48Updated 4 years ago
- XenC: open-source data selection tool for NLP☆60Updated 8 years ago
- Multilingual grapheme-to-phoneme conversion☆20Updated 6 years ago
- Text-to-Speech tutorial at SLTU 2016☆35Updated 8 years ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated 11 months ago
- Covering grammars for English and Russian text normalization☆60Updated 5 years ago
- ☆14Updated 5 years ago
- This repository describes our reproducible framework for assessing self-supervised representation learning from speech☆51Updated 3 years ago
- LSTM Language Model with Subword Units Input Representations☆42Updated 3 years ago
- ☆20Updated 6 years ago