227 Open source projects that are alternatives of or similar to Setk

ASR with PyTorch

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

Open source projects related to Snips https://snips.ai/.

pytorch-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.

kaldi-asr/kaldi is the official location of the Kaldi project.

🙊 A set of scripts to use in preparing a corpus for speech-to-text processing with the Kaldi Automatic Speech Recognition Library.

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

speech-aligner，是一个从“人声语音”及其“语言文本”，产生音素级别时间对齐标注的工具。speech-aligner, is a tool that generate phoneme-level alignment between human speech and its transcription

A Python wrapper for Kaldi

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model

Control anything with Siri voice commands.

Speech synthesis for ESP8266 using S.A.M. port

Voice Activity Detection based on Deep Learning & TensorFlow

Kaldi model converter to ONNX

A physical model of the human vocal tract using literate programming, based on Pink Trombone.

An example of the paper "reconstructing faces from voices"

Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time

An Android ChatBot powered by Watson Services - Assistant, Speech-to-Text and Text-to-Speech on IBM Cloud.

Text-to-Speech for Arduino

End-2-end speech synthesis with recurrent neural networks

Lingvo

Speech Recognition Using Tacotron

Neural speaker recognition/verification system based on Kaldi and Tensorflow

HoloBot is a reusable 3D interface that allows HoloLens & VR users to interact with any bot using Mixed Reality & Speech.

WaveNet vocoder

A React-Native Bridge for the Google Dialogflow (API.AI) SDK

A fast, high-quality neural vocoder.

The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus.

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

End-to-End Automatic Speech Recognition on PyTorch

an open source voice command macro software

Deep learning for audio denoising

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

Keras implementation of ‘’Deep Speaker: an End-to-End Neural Speaker Embedding System‘’ (speaker recognition)

A pure python module for reading and writing kaldi ark files

A simple example for use speech recognition baidu api with python.

A curated list of research papers and resources on code-switching

Computes the GMM-based Goodness of Pronunciation (GOP). Bases on Kaldi.

Speed to text in Unity iOS use Native Speech Recognition

Raspberry Pi + Nodejs = Speech Robot

Deep Learning-based Voice Conversion system

CTC end -to-end ASR for timit and 863 corpus.

Implementation of "Duration Informed Attention Network for Multimodal Synthesis" (https://arxiv.org/pdf/1909.01700.pdf) paper.

SDK & Sample to do speech recognition using websockets in Javascript

DELTA is a deep learning based natural language and speech processing platform.

🐸 collection of TTS papers

Implementation of Neural Voice Cloning with Few Samples Research Paper by Baidu

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Understanding emotions from audio files using neural networks and multiple datasets.

Yet another speech toolkit based on Kaldi and PyTorch

🙊 WIP software for creating speech recognition models.

A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.

Some simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as convenient as possible.

Python library for handling audio datasets.

Massively multilingual pronunciation mining

Predicting depression from acoustic features of speech using a Convolutional Neural Network.

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi