python | 高效使用统计语言模型kenlm:新词发现、分词、智能纠错等
Training an n-gram based Language Model using KenLM toolkit for Deep Speech 2
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。
翻译 - pycorrector是用于文本错误纠正的工具包。它的开发是为了方便设计,比较和共享深层文本纠错模型。
Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding
Whisper finetuned on VinBigdata-VLSP2020-100h + KenLM
CTC+Beam_Search+kenlm 是用于以汉字为声学模型建模单元的解码系统
Targoman SMT framework source code
CTC Decoder implementation with python only. Also supports language model decoding using KenLM.