Chinese text normalization for speech processing

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

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

An automatic speech recognition API

Neural speaker recognition/verification system based on Kaldi and Tensorflow

Implementing the paper -

Create a speech recognition system for programming by voice using Kaldi

This code repo is in reference to the Medium Article for setting up Kaldi on AWS

simple version of our torch kaldi toolkit, developed at the LIA by 2 apprentices. (@Chaanks & @vbrignatz)

Code for converting speech data into text using encoder-decoder model.

Create and adapt n-gram and JSGF language models, e.g. for Kaldi-ASR nnet3 chain models from Zamia-Speech

Contains code for Speaker Recognition.

Kaldi ASR Architeture Proposal

Tool to transform data from Nemo/Deepspeech format to Kaldi as described here — https://kaldi-asr.org/doc/data_prep.html

Scripts run on Kaldi toolkit on Kaggle's Tensorflow Speech Recognition Challenge

Nevis is a (sort of) all in one speech transcription library backed by Kaldi ASR.

Kaldi Implementation with Flask

This is a fork of PyTorch-Kaldi, 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. This repo adds support to use a GAN front-end for an ASR acoustic model.

ASR-WebUI : Deploying kaldi Model to Azure