Rnn ctcRecurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Stars: ✭ 220 (+947.62%)
Pytorch Kaldipytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+9885.71%)
Eeg DlA Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
Stars: ✭ 165 (+685.71%)
HasteHaste: a fast, simple, and open RNN library
Stars: ✭ 214 (+919.05%)
SpeakerDiarization RNN CNN LSTMSpeaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channels).
Stars: ✭ 56 (+166.67%)
LightnetEfficient, transparent deep learning in hundreds of lines of code.
Stars: ✭ 243 (+1057.14%)
NlstmNested LSTM Cell
Stars: ✭ 246 (+1071.43%)
wav2letterFacebook AI Research's Automatic Speech Recognition Toolkit
Stars: ✭ 6,026 (+28595.24%)
theano-recurrenceRecurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano
Stars: ✭ 40 (+90.48%)
Chameleon recsysSource code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
Stars: ✭ 202 (+861.9%)
Rnn For Joint NluPytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)
Stars: ✭ 176 (+738.1%)
air writingOnline Hand Writing Recognition using BLSTM
Stars: ✭ 26 (+23.81%)
Pytorch Sentiment AnalysisTutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+15180.95%)
DeepjazzDeep learning driven jazz generation using Keras & Theano!
Stars: ✭ 2,766 (+13071.43%)
KprnReasoning Over Knowledge Graph Paths for Recommendation
Stars: ✭ 220 (+947.62%)
E2e AsrPyTorch Implementations for End-to-End Automatic Speech Recognition
Stars: ✭ 106 (+404.76%)
novel writerTrain LSTM to writer novel (HongLouMeng here) in Pytorch.
Stars: ✭ 14 (-33.33%)
sequence-rnn-pySequence analyzing using Recurrent Neural Networks (RNN) based on Keras
Stars: ✭ 28 (+33.33%)
Rnn TransducerMXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks
Stars: ✭ 114 (+442.86%)
kospeechOpen-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
Stars: ✭ 456 (+2071.43%)
lstm harLSTM based human activity recognition using smart phone sensor dataset
Stars: ✭ 20 (-4.76%)
RnnvisA visualization tool for understanding and debugging RNNs
Stars: ✭ 162 (+671.43%)
Load forecastingLoad forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
Stars: ✭ 160 (+661.9%)
Char Rnn ChineseMulti-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Based on code of https://github.com/karpathy/char-rnn. Support Chinese and other things.
Stars: ✭ 192 (+814.29%)
StylenetA cute multi-layer LSTM that can perform like a human 🎶
Stars: ✭ 187 (+790.48%)
Crnn Audio ClassificationUrbanSound classification using Convolutional Recurrent Networks in PyTorch
Stars: ✭ 235 (+1019.05%)
Caption generatorA modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.
Stars: ✭ 243 (+1057.14%)
EBIM-NLIEnhanced BiLSTM Inference Model for Natural Language Inference
Stars: ✭ 24 (+14.29%)
Har Stacked Residual Bidir LstmsUsing deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
Stars: ✭ 250 (+1090.48%)
Pytorch Seq2seqTutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Stars: ✭ 3,418 (+16176.19%)
FARED for Anomaly DetectionOfficial source code of "Fast Adaptive RNN Encoder-Decoder for Anomaly Detection in SMD Assembly Machine"
Stars: ✭ 14 (-33.33%)
Pytorch Image Comp RnnPyTorch implementation of Full Resolution Image Compression with Recurrent Neural Networks
Stars: ✭ 146 (+595.24%)
EspressoEspresso: A Fast End-to-End Neural Speech Recognition Toolkit
Stars: ✭ 808 (+3747.62%)
Wav2letterFacebook AI Research's Automatic Speech Recognition Toolkit
Stars: ✭ 5,907 (+28028.57%)
EspnetEnd-to-End Speech Processing Toolkit
Stars: ✭ 4,533 (+21485.71%)
KospeechOpen-Source Toolkit for End-to-End Korean Automatic Speech Recognition.
Stars: ✭ 190 (+804.76%)
tf-ran-cellRecurrent Additive Networks for Tensorflow
Stars: ✭ 16 (-23.81%)
ArrayLSTMGPU/CPU (CUDA) Implementation of "Recurrent Memory Array Structures", Simple RNN, LSTM, Array LSTM..
Stars: ✭ 21 (+0%)
DrowsyDriverDetectionThis is a project implementing Computer Vision and Deep Learning concepts to detect drowsiness of a driver and sound an alarm if drowsy.
Stars: ✭ 82 (+290.48%)
timit-preprocessorExtract mfcc vectors and phones from TIMIT dataset
Stars: ✭ 14 (-33.33%)
kosrKorean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)
Stars: ✭ 25 (+19.05%)
dltfHands-on in-person workshop for Deep Learning with TensorFlow
Stars: ✭ 14 (-33.33%)