911 Open source projects that are alternatives of or similar to kospeech

Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition.

Korean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)

A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

Production First and Production Ready End-to-End Speech Recognition Toolkit

Transformer implementation speciaized in speech recognition tasks using Pytorch.

End-to-end ASR/LM implementation with PyTorch

End-to-End Automatic Speech Recognition on PyTorch

Production First and Production Ready End-to-End Speech Recognition Toolkit

an open-source implementation of sequence-to-sequence based speech processing engine

Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASSP 2020)

End-to-end speech recognition on AISHELL dataset.

A pytorch based end2end speech recognition system.

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

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

Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.

PyTorch Implementations for End-to-End Automatic Speech Recognition

transformer for ASR-systerm (via tensorflow2.0)

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

Lingvo

Sequence-to-Sequence Framework in PyTorch

Neutron: A pytorch based implementation of Transformer and its variants.

A PyTorch Implementation of "Attention Is All You Need"

MXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks

Implementation of State-of-the-art Text Classification Models in Pytorch

A TensorFlow Implementation of the Transformer: Attention Is All You Need

Simple implementations of NLP models. Tutorials are written in Chinese on my website https://mofanpy.com

Data Augmentation by Backtranslation (DAB) ヽ( •_-)ᕗ

A repo listing known open source voice tools, ordered by where they sit in the voice stack

A simple TensorFlow implementation of the Transformer

A wrapper around tensor2tensor to flexibly train, interact, and generate data for neural chatbots.

Minimalist NMT for educational purposes

Neural Machine Translation with Keras

Implementation of Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017.

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

list of efficient attention modules

Multi-turn dialogue baselines written in PyTorch

Transformers without Tears: Improving the Normalization of Self-Attention

Audio-Visual Speech Recognition using Sequence to Sequence Models

Molecular optimization by capturing chemist’s intuition using the Seq2Seq with attention and the Transformer

Witwicky: An implementation of Transformer in PyTorch.

pytorch implementation of Attention is all you need

텐서플로우와 머신러닝으로 시작하는 자연어처리(로지스틱회귀부터 트랜스포머 챗봇까지)

NLP Core Library and Model Zoo based on PaddlePaddle 2.0

Spokestack: give your React Native app a voice interface!

Facebook AI Research's Automatic Speech Recognition Toolkit

Code and data form the paper BERT Got a Date: Introducing Transformers to Temporal Tagging

Распознавание речи русского языка используя Tensorflow, обучаясь на базе Voxforge

"SOLQ: Segmenting Objects by Learning Queries", SOLQ is an end-to-end instance segmentation framework with Transformer.

Facebook AI Research's Automatic Speech Recognition Toolkit

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

End-to-End Speech Processing Toolkit

A Pytorch Implementation of Tacotron: End-to-end Text-to-speech Deep-Learning Model

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

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

A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.

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