2401 Open source projects that are alternatives of or similar to Lingvo

Speech Recognition in Asterisk with Vosk Server

ASR with PyTorch

A speech-to-text bot for discord with music commands and more using NodeJS. Ideally for controlling your Discord server using voice commands, can also be useful for hearing-impaired people.

Windows "say"

LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search

A proof-of-concept app using KeenASR SDK on Android. WE ARE HIRING: https://keenresearch.com/careers.html

how to use the Google Cloud Speech API to transcribe audio/video files.

SDKs and docs for Skit's speech to text service

TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis

AdaSpeech: Adaptive Text to Speech for Custom Voice

Vietnamese Speech Recognition

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

End-to-End Speech Processing Toolkit

Speech Recognition Using Tacotron

On-device streaming speech-to-text engine powered by deep learning

🧠 Leon is your open-source personal assistant.

Open tools and data for cloudless automatic speech recognition

Sequence-to-Sequence Framework in PyTorch

🎧 Automatic Speech Recognition: DeepSpeech & Seq2Seq (TensorFlow)

A PaddlePaddle implementation of ASR.

Implementation of Google Brain's WaveGrad high-fidelity vocoder (paper: https://arxiv.org/pdf/2009.00713.pdf). First implementation on GitHub.

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

🎙️ Handsfree Audio Development Interface

Voice control for your websites and applications

Implementation of a seq2seq model for Speech Recognition using the latest version of TensorFlow. Architecture similar to Listen, Attend and Spell.

This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )

Silero Models: pre-trained STT models and benchmarks made embarrassingly simple

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

💬 /so.nus/ STT (speech to text) for Node with offline hotword detection

An opensource speech-to-text software written in tensorflow

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

Stephanie is an open-source platform built specifically for voice-controlled applications as well as to automate daily tasks imitating much of an virtual assistant's work.

Descriptive Deep Learning

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

HTS-style full-context labels for JSUT v1.1

텐서플로우를 기초부터 응용까지 단계별로 연습할 수 있는 소스 코드를 제공합니다

SDK & Sample to do speech recognition using websockets in Javascript

A testing server for a speech to text service based on mozilla deepspeech

A collection of basic python modules for spoken natural language processing

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

Free, easy, portable audio engine for games

Localization/I18n: Incrementally update/translate your Strings files from .swift, .h, .m(m), .storyboard or .xib files.

Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine for Chinese.

A collection of Audio and Speech pre-trained models.

Adapt Intent Parser

Attention, I'm Trying to Speak: End-to-end speech synthesis (CS224n '18)

⦠ Angle: new speakable syntax for python 💡

the open-source virtual assistant for Ubuntu based Linux distributions

Program to benchmark various speech recognition APIs

speech-to-text in pytorch

💬 Speech to text, using the awesome engines readily available on the device.

Tutorials and my solutions to the Udacity NLP Nanodegree

Python module for evaluating ASR hypotheses (e.g. word error rate, word recognition rate).

Server & client for DeepSpeech using WebSockets for real-time speech recognition in separate environments

Tools to convert text to speech 📚💬

Simple speech linguistic AI with Python

A fast cnn-based vocoder

B.E.N.J.I.- The Impossible Missions Force's digital assistant