717 Open source projects that are alternatives of or similar to Espnet

Training open neural machine translation models

Official implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech

speech enhancement GAN on waveform/log-power-spectrum data using Improved WGAN

A library for real-time voice processing in web browsers

Phonetisaurus G2P

Real time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.

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

A python IO interface for data accessing in kaldi

📁 This repo makes it easy to download the raw audio files from AudioSet (32.45 GB, 632 classes).

使用 "Darknet yolov3-tiny" 进行车牌识别

Rev.ai Java SDK

User-space deniable data encryption client.

Tooling to play around with multilingual machine translation for Indian Languages.

Documentation and Wiki for SEPIA. Please post your questions and bug-reports here in the issues section! Thank you :-)

NLP-preprocessor for the SOVA-TTS project

Off-the-record (OTR) messaging protocol, purely in OCaml

Cross platform C++ library focusing on optimized machine translation on the consumer-grade device.

Keyword spotting using various architecture like convolutional vggnet , 1D convolutional network and CTC.

Chainer implementation of Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

ChainerPruner: Channel Pruning framework for Chainer

Transformer implementation speciaized in speech recognition tasks using Pytorch.

PyTorch implementation of the paper "NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity." (NeurIPS 2020)

Visualization for simple attention and Google's multi-head attention.

A fast implementation of Neural Image Caption by Chainer

基于javaFX的简单字幕处理桌面程序，集成在线翻译及语音转换

Quasi-Periodic Parallel WaveGAN Pytorch implementation

Jupyter notebooks for Chainer hands-on

A list of publically available audio data that anyone can download for ASR or other speech activities

This repo contains the source code in my personal column (https://zhuanlan.zhihu.com/zhaoyeyu), implemented using Python 3.6. Including Natural Language Processing and Computer Vision projects, such as text generation, machine translation, deep convolution GAN and other actual combat code.

24-hour Automatic Speech Recognition

Voice Conversion Challenge 2020 CycleVAE baseline system

A live speech recognition using Facebooks wav2vec 2.0 model.

HTK Toolkit with Linux 64 bit and Docker support

Wiki2SSML provides the WikiVoice markup language used for fine-tuning synthesised voice.

deep-learning platforms,framework,data（深度学习平台、框架、资料）

Practice your speech level in any language using speech recognition

WaveNet-Vocoder implementation with pytorch.

A Polymer 3+ webcomponent / button for doing speech recognition

Joint Dictionary Learning-based Non-Negative Matrix Factorization for Voice Conversion (TBME 2016)

Tacotron2 based engine for the SOVA-TTS project

SEPIA server to support open-source speech recognition via WebSocket connection.

Integration examples of Tanker's client-side encryption SDKs

Script to calculate SNR and SDR using python

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

GlottDNN vocoder and tools for training DNN excitation models

Node.js SDK for the Rev AI API

Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart. Objectives of the development are simplicity, modularity, controllability and multilinguality.

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

A merged version of multiple open-source German speech datasets.

Character Embeddings Recurrent Neural Network Text Generation Models

Implementation of "Automatic Portrait Segmentation" and "Deep Automatic Portrait Matting" with Chainer.

A speech dereverberation algorithm, also called wpe

LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation

IEEE ICASSP 21 - Quantum Convolution Neural Networks for Speech Processing and Automatic Speech Recognition

Python port of Moses tokenizer, truecaser and normalizer

Inverse Reinforcement Learning Argorithms

Web application providing a fully localised interface for text/website/document translation, analysis and generation powered by Apertium.

Simple sentence mixing tool (work in progress)

No description or website provided.

VoiceBridge - an AI-TOOLKIT Open Source C++ Speech Recognition Toolkit