v-yunbin Goto Github PK

acora

Fast multi-keyword search engine for text strings

add-noise

add noise of a certain SNR to audio files

addnoise

script and ubuntu executable to add noise to the given wavs

aegan-ad

Official pytorch implementation of AEGAN-AD

aliyun-oss-python-sdk

Aliyun OSS SDK for Python

audio-convolutional-neural-network

convolutional neural network for audio (Audio to Image)

audio2spectrogram

This tool can be used to convert mp3 to processable wav files, generate chunks of wav's and generate spectrograms.

audio_cut

语音切割，python ，webrtc

audioclassifier

A CNN audio classifier via spectrogram images.

bert-vits2-integration-train-txt-infer

适配windows的requirements.txt，加了个长文本分段推理和手机听书的api，非本专业，屎山代码

bert4torch

pytorch implement of transformers refer to bert4keras

bigcidian

Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.

chinese-nlp-corpus

Collections of Chinese NLP corpus

chinese-text-classification-pytorch

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

chinese_fuzzy_matching

100行解决中文模糊实体识别with字典树和编辑距离 Chinese fuzzy entity matching with prefix tree and distance editing

chinese_t2s

Translate traditional Chinese to Simplified Chinese.

chinesesegmentation

中文分词

chinesewiki

维基百科中文语料整理

cmudict

CMUdict maintenance, and tools

cn-text-normalizer

A python module that convert chinese written string to read string. 一个python包：将中文书面字符串转换为口语字符串。

cn2an

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

cvte_chain_model_finetune

finetune the chain model based on cvte open source model without traing any GMM for frame alignment

dacidian

DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)

dcase2020_task2_baseline

DCASE2020 Challenge Task 2 baseline system

deepsegment

A sentence segmenter that actually works!

dialog_corpus

用于训练中英文对话系统的语料库 Datasets for Training Chatbot System

docker-py-kaldi-asr

docker-python3-opencv4-ffmpeg4

Docker image including Python 3.7+, OpenCV 4.1+, FFmpeg 4.0+, based on Ubuntu

easybert

基于Pytorch的Bert应用，包括命名实体识别、情感分析、文本分类以及文本相似度等

emotion-finetuning-vits