Chenghao Mou

text-dedup. All-in-one text de-duplication

touchbar-lyric. Show synced lyric in the touch-bar with BetterTouchTool and NetEase APIs

pytorch-pQRNN. Implementation of pQRNN in PyTorch

embeddings. zero-vocab or low-vocab embeddings

transformer-pointer-generator. Transformer with pointer generator for machine translation

deduplicate-text-datasets. A modified version of Google's tool for pure text file

awesome-data-deduplication. An awesome list of data deduplication use cases, papers, tools, and methods.

chenghaomou.github.io. Personal Blog

simhash. Simhash in C++

karafuru. Traditional Chinese colors in your terminal

mini-vae. Minimal GMM VAE model for NLP

whisper_streaming. Whisper realtime streaming for long speech-to-text transcription and translation

lightning-grid-template. A minimal template for pytorch-lightning and grid.ai

idefics2-contract-qa. Jupyter Notebook