760 Open source projects that are alternatives of or similar to Asr_syllable

ASR with PyTorch

End-to-end ASR/LM implementation with PyTorch

Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection

A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

Implementation of papers for text classification task on DBpedia

This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.

Sequence-to-Sequence Framework in PyTorch

3D Dense Connected Convolutional Network (3D-DenseNet for action recognition)

采用深度学习方法进行刀具识别。

The official repository of the Eesen project

Auto Segmentation Criterion (ASG) implemented in pytorch

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

CNN, LSTM, NBOW, fasttext 中文文本分类

A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.

A Keras CTC implementation of Baidu's DeepSpeech for model experimentation

CNN+LSTM+CTC based OCR implemented using tensorflow.

Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)

End-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.

a deep accent recognition network

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.

SincNet is a neural architecture for efficiently processing raw audio samples.

an open-source implementation of sequence-to-sequence based speech processing engine

基于深度学习识别12306验证码

End-to-end variable length Captcha recognition using CNN+RNN+Attention/CTC (pytorch implementation). 端到端的不定长验证码识别

💳 Detecting the National Identification Cards with Deep Learning (Faster R-CNN)

用 Tensorflow.js 猜猜我的女朋友在想什么. A Tensorflow.js application for facial classification.

Keras implementation of the renowned publication "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" by Taigman et al. Pre-trained weights on VGGFace2 dataset.

text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.

Criss-Cross Attention for Semantic Segmentation in pure Pytorch with a faster and more precise implementation.

Punctuation restoration and spell correction experiments.

Draw a leader line in your web page.

Computer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.

A Unified Convolutional Neural Network Approach of Gesture Recognition and Fingertip Detection.

An Open Source Deep Learning Inference Engine Based on FPGA

An open source library for face detection in images. The face detection speed can reach 1000FPS.

Object classification with CIFAR-10 using transfer learning

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥

BertQA - Attention on Steroids

multi-label，classifier，text classification，多标签文本分类，文本分类，BERT，ALBERT，multi-label-classification

pytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"

The deeplearning algorithms implemented by tensorflow

Pytorch、Scikit-learn实现多种分类方法，包括逻辑回归（Logistic Regression）、多层感知机（MLP）、支持向量机（SVM）、K近邻（KNN）、CNN、RNN，极简代码适合新手小白入门，附英文实验报告（ACM模板）

This project is an aid to the blind. Till date there has been no technological advancement in the way the blind navigate. So I have used deep learning particularly convolutional neural networks so that they can navigate through the streets.

Machine learning, in numpy

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

基于CNN的验证码整体识别

A quick view of high-performance convolution neural networks (CNNs) inference engines on mobile devices.

Collections of model quantization algorithms

The Places365-CNNs for Scene Classification

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

Deep Learning Based Free Mobile Real-Time Face Landmark Detector. Contact:[email protected]

Chinese & English Cws Pos Ner Entity Recognition implement using CNN bi-directional lstm and crf model with char embedding.基于字向量的CNN池化双向BiLSTM与CRF模型的网络，可能一体化的完成中文和英文分词，词性标注，实体识别。主要包括原始文本数据，数据转换,训练脚本,预训练模型,可用于序列标注研究.注意：唯一需要实现的逻辑是将用户数据转化为序列模型。分词准确率约为93%，词性标注准确率约为90%，实体标注（在本样本上）约为85%。

Multi-turn dialogue baselines written in PyTorch

Deep Learning--深度学习