yuhangear's repositories
Speech-Resources
语音方向实验室/公司/资源/实习等，欢迎推荐或自荐（排名不分先后）
Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
bpemb
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
CIF-PyTorch
A PyTorch implementation of Continuous Integrate-and-Fire (CIF) mechanism/module/process in CIF-based speech recognition.
clash-for-linux
Linux 端使用 Clash 作为代理工具
DeepPhonemizer
Grapheme to phoneme conversion with deep learning.
frp
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
iwslt-2021
Systems submitted to IWSLT 2021 by the MT-UPC group.
LangChain-Chinese-Getting-Started-Guide
LangChain 的中文入门教程
NeuFA
Neural network-based forced alignment with bidirectional attention mechanism
Pet-GPT
Pet-GPT 是一个使用 PyQt 编写的桌面宠物程序，支持调用 OpenAI 的 GPT 进行上下文对话，然后主动找你聊天！
pytorch-edit-distance
Levenshtein edit-distance on PyTorch and CUDA
Resemblyzer
A python package to analyze and compare voices with deep learning
SpeechMix
Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together
tacotron2
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
wenet-hot
wenet-hot
wenet-hotwords
wenet-hotwords
xls-r-fine-tuning
xls-r fine-tuning script