halspeech Goto Github PK

chinese-poetry

最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

cino

CINO: Pre-trained Language Models for Chinese Minority (少数民族语言预训练模型)

classical-modern

非常全的文言文（古文）-现代文平行语料

cntk

Computational Network Toolkit (CNTK)

e2e_lfmmi

This is the implementation of paper CONSISTENT TRAINING AND DECODING FOR END-TO-END SPEECH RECOGNITIONUSING LATTICE-FREE MMI submitted to ICASSP2022

easyespnet

Making Espnet easier to use

eccc_dataset

eesen

The official repository of the Eesen project

forced-alignment

GSoC'16 RedHen Labs

hsoftmax

jointlytrained

Improving ASR by Joint Training with Translation

julius

Open-Source Large Vocabulary Continuous Speech Recognition Engine

julius_feat_extractor

kaldi

This is now the official location of the Kaldi project.

khmer-language-model-ulmfit

Khmer Language Model using ULMFiT

khmerwordsegmentation

Separate Khmer words from given sentences.

nict-tib1

NICT-Tib1: A public speech corpus of Lhasa dialect for benchmarking Tibetan language speech recognition systems developed by NICT

njukansai

thai-nlp-dataset

More than 43+ collections of Thai Natural Language Processing libraries. Update daily.

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

voice_ind

voxlingua107_sb

VoxLingua107 recipe for SpeechBrain

warp-ctc

Fast parallel CTC.