908 Open source projects that are alternatives of or similar to Rus-SpeechRecognition-LSTM-CTC-VoxForge

Docker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.

Tracing 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.

Presenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.

Graph convolution with tf.keras

🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

Deep Character CNN LSTM Encoder with Classification and Similarity Models

HF's ML for Audio study group

Chinese speech recognition

SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth

A tutorial exploring multiple approaches to deploy a trained TensorFlow (or Keras) model or multiple models for prediction.

An API-first distributed deployment system of deep learning models using timeseries data to predict the behaviour of systems

React app using the Watson Speech to Text service to transform voice audio into written text.

No description or website provided.

Node.js SDK for the Rev AI API

Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2

Implementations of machine learning algorithm by Python 3

RNN(Recurrent Nerural network) model which recognize hand-gestures drawing 5 figures.

Speechly public API definitions and generated code

Playground for implementing custom layers and other components compatible with keras, with the purpose to learn the framework better and perhaps in future offer some utils for others.

An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.

Recognize Digits using Deep Neural Networks in Google Chrome live!

Vanilla LSTM with numpy

A MXNet implementation of Baidu's DeepSpeech architecture

An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data

Various implementations and projects on CNN, RNN, LSTM, GAN, etc

LSTM sentiment analysis. Please look at my another repo for SVM and Naive algorithem

A PyTorch implementation of the Deep Audio-Visual Speech Recognition paper.

This repo contains a PyTorch implementation of a BiLSTM-CRF model for named entity recognition task.

Optical character recognition Using Deep Learning

RNN-LSTM that learns passwords from a starting list

Small Robot, Toy Robot platform

Translating English sentences to Marathi using Neural Machine Translation

Word-accurate timestamps for Qur'anic audio.

Implementation of One Shot Learning using Convolutional Siamese Networks on Omniglot Dataset

Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".

host load prediction with Long Short-Term Memory in cloud computing

Real-time fall detection using two-stream convolutional neural net (CNN) with Motion History Image (MHI)

Gaussian Mixture Convolutional AutoEncoder applied to CT lung scans from the Kaggle Data Science Bowl 2017

An React client library for Speechly API

Cypress + Docker + CircleCI Workflows = ❤️

Neural network that solves math equations on the character level

Recurrent Additive Networks for Tensorflow

Long audio alignment using Kaldi

This repository contains Machine Learning projects that involve the steps starting from data collection to deployment

No description or website provided.

Experiments with Hugging Face 🔬 🤗

Speech-to-text based on wav2letter built for transfer learning

The open source intelligent personal assistant

Keras-Tensorflow implementation of complex-valued convolutional neural networks

Tensorflow Keras implementation of ordinal regression using consistent rank logits (CORAL) by Cao et al. (2019)

Use Google Speech-to-Text API to do real-time live stream caption on Unity! Best when combined with your virtual character!

ML Prediction of Bible Topics and Passages (Python / React)

Recurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano

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。

Official implementation of the paper "Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning Algorithms": https://arxiv.org/abs/1909.01779 To appear at the next NeurIPS2019 DRL-Workshop

Sequence analyzing using Recurrent Neural Networks (RNN) based on Keras

Speech to text bot for Discord using Mozilla's DeepSpeech

Transformer implementation speciaized in speech recognition tasks using Pytorch.

Generate Thai Songs' lyrics using Deep Learning

Extract mfcc vectors and phones from TIMIT dataset