Pinned Repositories
acoustic_embeddings
Amphion
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
friendscope
A scientific friendship assessment tool built with Next.js that helps evaluate and improve interpersonal relationships through data-driven insights.
g2pK
g2pK: g2p module for Korean
gpt_academic
为ChatGPT/GLM提供图形交互界面，特别优化论文阅读润色体验，模块化设计支持自定义快捷按钮&函数插件，支持代码块表格显示，Tex公式双显示，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持清华chatglm等本地模型。兼容复旦MOSS, llama, rwkv, 盘古, newbing, claude等
k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
pycorrector
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。
RVC-CLI
Voice data <= 10 mins can also be used to train a good VC model!
treya-lin's Repositories
treya-lin/acoustic_embeddings
treya-lin/Amphion
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
treya-lin/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
treya-lin/g2pK
g2pK: g2p module for Korean
treya-lin/gpt_academic
为ChatGPT/GLM提供图形交互界面，特别优化论文阅读润色体验，模块化设计支持自定义快捷按钮&函数插件，支持代码块表格显示，Tex公式双显示，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持清华chatglm等本地模型。兼容复旦MOSS, llama, rwkv, 盘古, newbing, claude等
treya-lin/k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
treya-lin/PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
treya-lin/pycorrector
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。
treya-lin/RVC-CLI
Voice data <= 10 mins can also be used to train a good VC model!
treya-lin/sherpa
Speech-to-text server framework with next-gen Kaldi