jinsongpan Goto Github PK

deepspeech

A TensorFlow implementation of Baidu's DeepSpeech architecture

deepspeechrecognition

A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型

dialog_corpus

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

diin-in-keras

Reproducing Densely Interactive Inference Network in Keras

disan

Code of Directional Self-Attention Network (DiSAN)

dive-into-dl-pytorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

django-socketio

WebSockets for Django

djangoblog

🍺基于Django的博客系统

dmai-en-speech-assess-2-doc

docker_practice

Learn and understand Docker technologies, with real DevOps practice!

elasticsearch-definitive-guide

欢迎加QQ群：109764489，贡献力量！

elasticsearch-py

Official Python low-level client for Elasticsearch.

electra

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

ernie

An Implementation of ERNIE For Language Understanding (including Pre-training models and Fine-tuning tools)

espnet

End-to-End Speech Processing Toolkit

fairseq

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

fasttext

Library for fast text representation and classification.

forced-alignment-tools

A collection of links and notes on forced alignment tools

from_video_get_asr_traindata

这个工程的目的是从视频中获取语音识别的训练数据，用于训练字幕自动生成

g2p-seq2seq

G2P with Tensorflow

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

gfwlist

The one and only one gfwlist here

hanzi_char_featurizer

汉字字符特征提取器 (featurizer)，提取汉字的特征（发音特征、字形特征）用做深度学习的特征

insuranceqa-corpus-zh

OpenData in insurance area for Machine Learning Tasks

kaggle-quora-question-pairs

Kaggle：Quora Question Pairs, 4th/3396 (https://www.kaggle.com/c/quora-question-pairs)

kaldi

This is the official location of the Kaldi project.

kaldi-gstreamer-server

Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.

keras

Deep Learning for humans

langid.py

Stand-alone language identification system

language-recognition

CNN to classify samples of voice recordings into the language that was spoken