ProcessorOntology-driven Linked Data processor and server for SPARQL backends. Apache License.
Stars: ✭ 54 (+157.14%)
voice zaloaidentifying gender and regional accent from speech
Stars: ✭ 35 (+66.67%)
name2genderExtrapolate gender from first names using Naïve-Bayes and PyTorch Char-RNN
Stars: ✭ 24 (+14.29%)
DeepsleepnetDeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
Stars: ✭ 200 (+852.38%)
dnd-lstmA Python(PyTorch) implementation of memory augmented neural network based on Ritter et al. (2018). Been There, Done That: Meta-Learning with Episodic Recall. ICML.
Stars: ✭ 30 (+42.86%)
etl[READ-ONLY] PHP - ETL (Extract Transform Load) data processing library
Stars: ✭ 279 (+1228.57%)
QuantumSpeech-QCNNIEEE ICASSP 21 - Quantum Convolution Neural Networks for Speech Processing and Automatic Speech Recognition
Stars: ✭ 71 (+238.1%)
MetaTraderForecastRNN based Forecasting App for Meta Trader and similar trading platforms
Stars: ✭ 103 (+390.48%)
pytorch audioaudio processing module for pytorch:stft, istft
Stars: ✭ 33 (+57.14%)
Lyrics-to-Audio-AlignmentAligns text (lyrics) with monophonic singing voice (audio). The algorithm uses structural segmentation to segment the audio into structures and then uses hidden markov models to obtain alignment within segments. The final alignment is concatenation of time stamps of lyrics within the segments for each song.
Stars: ✭ 57 (+171.43%)
Charades AlgorithmsActivity Recognition Algorithms for the Charades Dataset
Stars: ✭ 181 (+761.9%)
favorite-research-papersListing my favorite research papers 📝 from different fields as I read them.
Stars: ✭ 12 (-42.86%)
Deep AlgotradingA resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading
Stars: ✭ 173 (+723.81%)
ctc-asrEnd-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.
Stars: ✭ 112 (+433.33%)
A chronology of deep learningTracing back and exposing in chronological order the main ideas in the field of deep learning, to help everyone better understand the current intense research in AI.
Stars: ✭ 47 (+123.81%)
Img2VecCosSim-Django-PytorchExtract a feature vector for any image and find the cosine similarity for comparison using Pytorch. I have used ResNet-18 to extract the feature vector of images. Finally a Django app is developed to input two images and to find the cosine similarity.
Stars: ✭ 20 (-4.76%)
tf-attend-infer-repeatTensorFlow-based implementation of "Attend, Infer, Repeat" paper (Eslami et al., 2016, arXiv:1603.08575).
Stars: ✭ 44 (+109.52%)
pred-rnnPredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
Stars: ✭ 115 (+447.62%)
torchsubbandPytorch implementation of subband decomposition
Stars: ✭ 63 (+200%)
Deep News SummarizationNews summarization using sequence to sequence model with attention in TensorFlow.
Stars: ✭ 167 (+695.24%)
ASR-Audio-Data-LinksA list of publically available audio data that anyone can download for ASR or other speech activities
Stars: ✭ 179 (+752.38%)
TinyCogSmall Robot, Toy Robot platform
Stars: ✭ 29 (+38.1%)
multilingual kwsFew-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
Stars: ✭ 122 (+480.95%)
VoiceDictation迅飞 语音听写 WebAPI - 把语音(≤60秒)转换成对应的文字信息,让机器能够“听懂”人类语言,相当于给机器安装上“耳朵”,使其具备“能听”的功能。
Stars: ✭ 36 (+71.43%)
machine-learning-data-pipelinePipeline module for parallel real-time data processing for machine learning models development and production purposes.
Stars: ✭ 22 (+4.76%)
keras-utility-layer-collectionCollection of custom layers and utility functions for Keras which are missing in the main framework.
Stars: ✭ 63 (+200%)
modulesThe official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.
Stars: ✭ 25 (+19.05%)
Human-Activity-RecognitionHuman activity recognition using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six categories (WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, LAYING).
Stars: ✭ 16 (-23.81%)
VoiceBridgeVoiceBridge - an AI-TOOLKIT Open Source C++ Speech Recognition Toolkit
Stars: ✭ 17 (-19.05%)
MimickCode for Mimicking Word Embeddings using Subword RNNs (EMNLP 2017)
Stars: ✭ 152 (+623.81%)
KodiSharpUse Kodi python APIs in C#, and write rich addons using the .NET framework/Mono
Stars: ✭ 22 (+4.76%)
Stock Price PredictorThis project seeks to utilize Deep Learning models, Long-Short Term Memory (LSTM) Neural Network algorithm, to predict stock prices.
Stars: ✭ 146 (+595.24%)
speech-to-text-code-patternReact app using the Watson Speech to Text service to transform voice audio into written text.
Stars: ✭ 37 (+76.19%)
SSNM-Coseg[AAAI20] Deep Object Co-segmentation via Spatial-Semantic Network Modulation(Oral paper)
Stars: ✭ 21 (+0%)
ACTAlternative approach for Adaptive Computation Time in TensorFlow
Stars: ✭ 16 (-23.81%)
spokestack-iosSpokestack: give your iOS app a voice interface!
Stars: ✭ 27 (+28.57%)
kaldi ag trainingDocker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.
Stars: ✭ 14 (-33.33%)
Deep Learning ResourcesA Collection of resources I have found useful on my journey finding my way through the world of Deep Learning.
Stars: ✭ 141 (+571.43%)
LSTM-TensorSparkImplementation of a LSTM with TensorFlow and distributed on Apache Spark
Stars: ✭ 40 (+90.48%)
postchildren-desktop👨👦👦 A E2E test visualization tool (get along with postman and postwoman)
Stars: ✭ 23 (+9.52%)
CaptionThis"Caption This" is an iOS app that adds real-time captions to videos for Instagram Stories
Stars: ✭ 12 (-42.86%)
PCPMPresenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.
Stars: ✭ 21 (+0%)
wav2vec2-liveA live speech recognition using Facebooks wav2vec 2.0 model.
Stars: ✭ 205 (+876.19%)
leopardOn-device speech-to-text engine powered by deep learning
Stars: ✭ 354 (+1585.71%)
datastories-semeval2017-task6Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".
Stars: ✭ 20 (-4.76%)
InimesedAn Android app that lets you search your contacts by voice. Internet not required. Based on Pocketsphinx. Uses Estonian acoustic models.
Stars: ✭ 65 (+209.52%)
nemesystGeneralised and highly customisable, hybrid-parallelism, database based, deep learning framework.
Stars: ✭ 17 (-19.05%)
good-speech-web-clientPractice your speech level in any language using speech recognition
Stars: ✭ 26 (+23.81%)