minglunhan Goto Github PK

4675-scifi-collections

chinese NLP corpus of chinese science fiction,chinese science fiction corpus : About 4675 Chinese science fiction novels 大约有4675本科幻小说，中文科幻小说自然语言处理语料库，中文科幻小说文本语料库，中文科幻小说文本数据库，科幻小说语料

acad-homepage.github.io

AcadHomepage: A Modern and Responsive Academic Personal Homepage

aisystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

awesome-large-audio-models

Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

best-of-streamlit

🏆 A ranked gallery of awesome streamlit apps built by the community

books

Book PDF

books-free-books

Free Books

chatglm-finetuning

基于ChatGLM-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning等

chatpaper

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

chinese_speech_pretrain

chinese speech pretrained models

cif-coldec

[ICASSP 2022] Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection

cif-hieradist

[INTERSPEECH 2023] Knowledge Transfer from Pre-trained Language Models to Cif-based Recognizers via Hierarchical Distillation

cif-pytorch

[ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-Fire mechanism).

cognitive-science

主题：计算认知科学(Computational Cognitive Science)。此仓库诞生背景为IA003结业BP，仍处于萌芽期，内容设置有待转正。下一次大规模更新估计在三四年之后。

ebooks

收藏的一些经典的历史、政治、心理、哲学、数学、计算机方面电子书(约10万本）

espnet-asrtts

ASR-TTS experiments based on espnet. recipe for librispeech available

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fastspeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

fastspeech2_ljspeech

Optimizing the FastSpeech2 model using the LJSpeech Dataset

introrl

Intro to Reinforcement Learning (强化学习纲要）

ivector-xvector

Extract xvector and ivector under kaldi

langchain_csv

liblio

可醉楼藏书

lora-diffusion-models

Using Low-rank adaptation to quickly fine-tune diffusion models.

meeting_summarization_dataset

Codes for processing meeting summarization datasets AMI and ICSI.

minimal-light

A simple and elegant Jekyll theme for an academic personal homepage

montreal-forced-aligner

Command line utility for forced alignment using Kaldi

mscoco-cn

Enriching MS-COCO with Chinese sentences and tags for cross-lingual multimedia tasks

ofa

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

pyctcdecode

A fast and lightweight python-based CTC beam search decoder for speech recognition.