wy192 Goto Github PK

ai_beatmap_generator

尝试使用神经网络生成音乐游戏Malody的谱面。

aidatatang_1505zh

api-demo

audfprint

Landmark-based audio fingerprinting

awesome-diarization

A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

char-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

cleanlab

The standard package for machine learning with noisy labels and finding mislabeled data. Works with most datasets and models.

comic

This project is a full stack project written in Python language and Django framework for front end integration. Models used are Object detection, Image Captioning, Google Speech API for text to speech and speech to text.

ctranslate2

Fast inference engine for Transformer models

cvpr2020-code

CVPR 2020 论文开源项目合集

d-tdnn

PyTorch implementation of Densely Connected Time Delay Neural Network

ddc

Dance Dance Convolution dataset tools and models

decryptlogin

DecryptLogin: APIs for loginning some websites by using requests.

deep-speaker

Deep Speaker: an End-to-End Neural Speaker Embedding System.

deep_blur_detection_and_classification

End-to-end network for blur detection and classification (presented at PG 2018)

dejavu

Audio fingerprinting and recognition in Python

demo

dvqa

Deep learning-based Video Quality Assessment

ecapa-tdnn

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)

edetection_v2_1

Element Detection of Scanned Comic Book Images

encoder_decoder

Four styles of encoder decoder model by Python, Theano, Keras and Seq2Seq

espnet

End-to-End Speech Processing Toolkit

etdnn

Code for paper in "ECAPA-TDNN Based Depression Detection from Clinical Speech"

factorized-tdnn

PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi

gitignore

A collection of useful .gitignore templates

image-quality-assessment

Convolutional Neural Networks to predict the aesthetic and technical quality of images.

inaspeechsegmenter

CNN-based audio segmentation toolkit. Allows to detect speech, music and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

information

一些公用的代码，资料文件，公司项目

kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

kaldifeat

Kaldi-compatible feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API