strivetao Goto Github PK

attentionbasedprosodyprediction

Encoder and Decoder and Attention Based Prosody Prediction

automatic-prosody-annotation

chinese_speech_pretrain

chinese speech pretrained models

code-switching-contest

基于单语种语料的中英混合语音识别算法-同花顺算法挑战赛-2021年9-10月双月赛

code-switching-papers

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

e2e_lfmmi

E2E system with LF-MMI; word N-gram for Mandarin

fastasr

这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 推理模型是基于目前最先进的conformer模型，使用10000+小时的wenetspeech数据集训练得到， 所以识别效果也很好，可以媲美许多商用的ASR软件。

funasr

A Fundamental End-to-End Speech Recognition Toolkit

incremental-asr-processing

We are evaluating current incremental ASR systems on conversational dialogues

kaldi-dnn-ali-gop

Forced alignment and Goodness of Pronunciation (GOP) with DNN support. Bases on Kaldi.

las

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

lerangit

magic-cs-20220920

masr

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

speechocean762

The speechocean762 dataset for pronunciation scoring tasks.

torch_cif

A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.

warp-rna

Recurrent Neural Aligner