Kaldi

Category: Text to Speech

Industries: Software Development

A toolset for automatic speech recognition called Kaldi supports deep neural networks, feature-space discriminative training, boosted MMI and MCE training, MMI, and linear transformations.

A toolset for automatic speech recognition called Kaldi supports deep neural networks, feature-space discriminative training, boosted MMI and MCE training, MMI, and linear transformations.

Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers. For more detailed history and list of contributors see History of the Kaldi project.

20M+ Downloads
5/5

#1 in Magazines & Newspapers

Speechify is the #1 audio reader in the world. Get through books, docs, articles, PDFs, email – anything

you read – faster.

Sir Richard Branson

Speechify is absolutely brilliant. Growing up with dyslexia this would have made a big difference. I’m so glad to have it today.

Sir Richard Branson

Highlights

Pricing
Free: Open Source
ProsCons
Open SourceComplicated To set-up
Provides high quality ASR results, lots of freedom on how to do thingsThe framework is difficult to use, and lots of times require an in depth understanding of ASR concepts
C++ makes it fastThe neural network part of kaldi is out-of-dated, the pipe style command line makes it hard to run on Windows system
Accurate

Kaldi reviews

Setup and installation is very complicated

- Qasim A- Data Science Engineer

It's open-sourced, but very well maintained by the core group of Johns Hopkins University's speech recognition laboratory. It has been offering a great suite of tools and libraries for speech scientists to utilize to perform their research experiments with ease as well as for industry practitioners to exploit to build business solutions for customers who are interested in paying for dependable speech recognition solutions. It also supports various neural network architectures that can be useful for any sequential processing. Given that we're in the era of deep learning booming, this tool is a real gem for any machine learning engineer to be able to use to build and evaluate neural network based systems for various tasks.

- Kyu H. - Principal Machine Learning Scientist

Transcription Accuracy. Also the libraries are very helpful

- Internal Consultant in Airlines/Aviation

What is Speechify?

Speechify is one of the most popular audio tools in the world. Our Google Chrome extension, web app, iOS app, and Android app help anyone listen to content at any speed they want. You can also listen to content in over 30 different voices or languages.

How can Speechify turn anything into an audiobook?

Speechify provides anyone with an audio play button that they can add on top of their content to turn it into an audiobook. With the Speechify app on iOS and Android, anyone can take this information on the go.

Learn more about text to speech online, for iOS, Mac, Android, and Chrome Extension.

Speechify is the #1 audio reader in the world

Get through books, docs, articles, PDFs, email – anything you read – faster.

4.6/5

20M+ downloads

Trending products

Choose Language :