ESPnet is an end-to-end speech processing toolkit, mainly focuses on end-to-end speech recognition and end-to-end text-to-speech.
ESPnet uses chainer as a main deep learning engine, and also follows Kaldi style data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments.
ESPnet is free and open source software.
Features include:
- Hybrid CTC/attention based end-to-end ASR:
- Fast/accurate training with CTC/attention multitask training.
- CTC/attention joint decoding to boost monotonic alignment decoding.
- Encoder: VGG-like CNN + BiRNN (LSTM/GRU), sub-sampling BiRNN (LSTM/GRU) or Transformer.
- Attention: Dot product, location-aware attention, variants of multihead.
- Incorporate RNNLM/LSTMLM trained only with text data.
- Batch GPU decoding.
- Transducer based end-to-end ASR:
- Available: RNN-Transducer, Transformer-Transducer, Transformer/RNN-Transducer.
- Support attention extension and VGG-Transformer (encoder).
- Tacotron2 based end-to-end TTS.
- Transformer based end-to-end TTS.
- Feed-forward Transformer (a.k.a. FastSpeech) based end-to-end TTS.
- Transformer based end-to-end ST.
- Transformer based end-to-end MT.
- Flexible network architecture thanks to chainer and pytorch.
- Kaldi style complete recipe:
- Support numbers of ASR recipes (WSJ, Switchboard, CHiME-4/5, Librispeech, TED, CSJ, AMI, HKUST, Voxforge, REVERB, etc).
- Support numbers of TTS recipes with a similar manner to the ASR recipe (LJSpeech, LibriTTS, M-AILABS, etc).
- Support numbers of ST recipes (Fisher-CallHome Spanish, Libri-trans, IWSLT’18, How2, Must-C, Mboshi-French, etc).
- Support numbers of MT recipes (IWSLT’16, the above ST recipes etc).
- Support speech separation and recognition recipe (WSJ-2mix).
- State-of-the-art performance in several ASR benchmarks (comparable/superior to hybrid DNN/HMM and CTC).
- State-of-the-art performance in several ST benchmarks (comparable/superior to cascaded ASR and MT).
- Flexible front-end processing thanks to kaldiio and HDF5 support.
- Tensorboard based monitoring.
Website: espnet.github.io/espnet
Support: GitHub Code Repository
Developer: Tomoki Hayashi, Hirofumi Inaguma, Naoyuki Kamo, Shigeki Karita, and many contributors
License: Apache License 2.0
ESPnet is written in Python. Learn Python with our recommended free books and free tutorials.
Return to Speech Recognition Tools
Popular series | |
---|---|
The largest compilation of the best free and open source software in the universe. Each article is supplied with a legendary ratings chart helping you to make informed decisions. | |
Hundreds of in-depth reviews offering our unbiased and expert opinion on software. We offer helpful and impartial information. | |
The Big List of Active Linux Distros is a large compilation of actively developed Linux distributions. | |
Replace proprietary software with open source alternatives: Google, Microsoft, Apple, Adobe, IBM, Autodesk, Oracle, Atlassian, Corel, Cisco, Intuit, and SAS. | |
Awesome Free Linux Games Tools showcases a series of tools that making gaming on Linux a more pleasurable experience. This is a new series. | |
Machine Learning explores practical applications of machine learning and deep learning from a Linux perspective. We've written reviews of more than 40 self-hosted apps. All are free and open source. | |
New to Linux? Read our Linux for Starters series. We start right at the basics and teach you everything you need to know to get started with Linux. | |
Alternatives to popular CLI tools showcases essential tools that are modern replacements for core Linux utilities. | |
Essential Linux system tools focuses on small, indispensable utilities, useful for system administrators as well as regular users. | |
Linux utilities to maximise your productivity. Small, indispensable tools, useful for anyone running a Linux machine. | |
Surveys popular streaming services from a Linux perspective: Amazon Music Unlimited, Myuzi, Spotify, Deezer, Tidal. | |
Saving Money with Linux looks at how you can reduce your energy bills running Linux. | |
Home computers became commonplace in the 1980s. Emulate home computers including the Commodore 64, Amiga, Atari ST, ZX81, Amstrad CPC, and ZX Spectrum. | |
Now and Then examines how promising open source software fared over the years. It can be a bumpy ride. | |
Linux at Home looks at a range of home activities where Linux can play its part, making the most of our time at home, keeping active and engaged. | |
Linux Candy reveals the lighter side of Linux. Have some fun and escape from the daily drudgery. | |
Getting Started with Docker helps you master Docker, a set of platform as a service products that delivers software in packages called containers. | |
Best Free Android Apps. We showcase free Android apps that are definitely worth downloading. There's a strict eligibility criteria for inclusion in this series. | |
These best free books accelerate your learning of every programming language. Learn a new language today! | |
These free tutorials offer the perfect tonic to our free programming books series. | |
Linux Around The World showcases usergroups that are relevant to Linux enthusiasts. Great ways to meet up with fellow enthusiasts. | |
Stars and Stripes is an occasional series looking at the impact of Linux in the USA. |