kenlm 开源项目推荐（37 个）

shibing624 /pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

DeutscheKI /tevr-asr-tool

State-of-the-art (ranked #1 Aug 2022) German Speech Recognition in 284 lines of C++. This is a 100% private 100% offline 100% free CLI tool.

kmario23 /KenLM-training

Training an n-gram based Language Model using KenLM toolkit for Deep Speech 2

Sundy1219 /ctc_beam_search_lm

CTC+Beam_Search+kenlm 是用于以汉字为声学模型建模单元的解码系统

pooya-mohammadi /persian-spell-checker-kenlm

A complete instruction for training a Persian spell checker and a language model based on SymSpell and KenLM, respectively using Wikipedia dataset.

loretoparisi /wave2vec-recognize-docker

Wave2vec 2.0 Recognize pipeline

racai-ai /RobinASR

Romanian Automatic Speech Recognition from the ROBIN project

Targoman /TargomanSMT

Targoman SMT framework source code

Lednik7 /nto-ai-text-recognition

Optical Character Recognition + Instance Segmentation for russian and english languages

christopherthompson81 /vernacula

ONNX speech pipeline library for ASR (diarization, VAD), and TTS

tokestermw /spacy_kenlm

🎲 KenLM extension for spaCy 2.0.

levyfan /kenlm-jni

A Java JNI wrapper for KenLM: Faster and Smaller Language Model Queries

LuluW8071 /Automatic-Speech-Recognition-with-PyTorch

Real-Time ASR with CNN-BiLSTM: End-to-End Live Streaming Using PyTorch Lightning⚡

mgxv /SwiftType

A macOS IME with a floating candidate window for word completions, spell corrections, and next-word predictions powered by KenLM n-gram models.

teodor-cotet /RoGEC

Neural Grammatical Error Correction for Romanian using Transformer

mozilla /scorertool

INACTIVE - http://mzl.la/ghe-archive - Generate language models from OSCAR corpora

fquirin /kaldi-adapt-lm

Create and adapt n-gram and JSGF language models, e.g. for Kaldi-ASR nnet3 chain models from Zamia-Speech

Msparihar /Transcriber

Developed an AI tool to automatically generate captions and transcripts for YouTube videos in 67 languages and can generate summarized texts in 133 languages.

LuluW8071 /VocalMind

Automatic Speech Recognition using Conformer with Speech Sentiment Analysis & Text Summarizer

mpoyraz /ngram-lm-wiki

Scripts to train a n-gram language models on Wikipedia articles