diff --git a/README.md b/README.md index 9330c005f..fd2ab06de 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,12 @@ [中文版](README_cn.md) -# DeepSpeech on PaddlePaddle +# PaddlePaddle ASR toolkit ![License](https://img.shields.io/badge/license-Apache%202-red.svg) ![python version](https://img.shields.io/badge/python-3.7+-orange.svg) ![support os](https://img.shields.io/badge/os-linux-yellow.svg) -*DeepSpeech on PaddlePaddle* is an open-source implementation of end-to-end Automatic Speech Recognition (ASR) engine, with [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) platform. Our vision is to empower both industrial application and academic research on speech recognition, via an easy-to-use, efficient and scalable implementation, including training, inference & testing module, and demo deployment. +*PaddleASR* is an open-source implementation of end-to-end Automatic Speech Recognition (ASR) engine, with [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) platform. Our vision is to empower both industrial application and academic research on speech recognition, via an easy-to-use, efficient, samller and scalable implementation, including training, inference & testing module, and deployment. ## Models @@ -19,7 +19,7 @@ ## Setup * python>=3.7 -* paddlepaddle>=2.0.0 +* paddlepaddle>=2.1.0 Please see [install](docs/install.md). diff --git a/README_cn.md b/README_cn.md index b50d205e9..f124ccf09 100644 --- a/README_cn.md +++ b/README_cn.md @@ -1,13 +1,13 @@ [English](README.md) -# DeepSpeech on PaddlePaddle +# PaddlePaddle ASR toolkit ![License](https://img.shields.io/badge/license-Apache%202-red.svg) ![python version](https://img.shields.io/badge/python-3.7+-orange.svg) ![support os](https://img.shields.io/badge/os-linux-yellow.svg) -*DeepSpeech on PaddlePaddle*是一个采用[PaddlePaddle](https://github.com/PaddlePaddle/Paddle)平台的端到端自动语音识别（ASR）引擎的开源项目， -我们的愿景是为语音识别在工业应用和学术研究上，提供易于使用、高效和可扩展的工具，包括训练，推理，测试模块，以及 demo 部署。同时，我们还将发布一些预训练好的英语和普通话模型。 +*PaddleASR*是一个采用[PaddlePaddle](https://github.com/PaddlePaddle/Paddle)平台的端到端自动语音识别（ASR）引擎的开源项目， +我们的愿景是为语音识别在工业应用和学术研究上，提供易于使用、高效、小型化和可扩展的工具，包括训练，推理，以及 部署。 ## 模型 @@ -20,7 +20,7 @@ ## 安装 * python>=3.7 -* paddlepaddle>=2.0.0 +* paddlepaddle>=2.1.0 参看 [安装](docs/install.md)。 diff --git a/docs/src/asr_postprocess.md b/docs/src/asr_postprocess.md new file mode 100644 index 000000000..933e5add9 --- /dev/null +++ b/docs/src/asr_postprocess.md @@ -0,0 +1,5 @@ +# ASR PostProcess + +## Text corrector +* [pycorrector](https://github.com/shibing624/pycorrector) +ERNIE on paddlepaddle. diff --git a/docs/src/chinese_syllable.md b/docs/src/chinese_syllable.md index d5ae3cd4a..7ccfe3dae 100644 --- a/docs/src/chinese_syllable.md +++ b/docs/src/chinese_syllable.md @@ -1,10 +1,19 @@ # chinese syllable + + ## Syllable + * [List of Syllables in Pinyin](https://resources.allsetlearning.com/chinese/pronunciation/syllable) -The word syllable is a term referring to the units of a word, composed on an (optional) initial, a final, and a tone. -The word "syllable" is 音节 (yīnjié) in Chinese. Most spoken syllables in Mandarin Chinese correspond to one written Chinese character. -There are a total of 410 common pinyin syllables. + The word syllable is a term referring to the units of a word, composed on an (optional) initial, a final, and a tone. + + The word "syllable" is 音节 (yīnjié) in Chinese. + + Most spoken syllables in Mandarin Chinese correspond to one written Chinese character. + + There are a total of 410 common pinyin syllables. + + * [Rare syllable](https://resources.allsetlearning.com/chinese/pronunciation/Rare_syllable) @@ -13,10 +22,12 @@ There are a total of 410 common pinyin syllables. * [Mandarin Chinese Phonetics](http://www.zein.se/patrick/chinen8p.html) * [chinese phonetics](https://www.easymandarin.cn/online-chinese-lessons/chinese-phonetics/) -Chinese Characters, called “Hanzi”, are the writing symbols of the Chinese language. -Pinyin is the Romanization of a phonetic notation for Chinese Characters. -Each syllable is composed of three parts: initials, finals, and tones. -In the Pinyin system there are 23 initials, 24 finals, 4 tones and a neutral tone. + Chinese Characters, called “Hanzi”, are the writing symbols of the Chinese language. + Pinyin is the Romanization of a phonetic notation for Chinese Characters. + Each syllable is composed of three parts: initials, finals, and tones. + In the Pinyin system there are 23 initials, 24 finals, 4 tones and a neutral tone. + + ## Pinyin * [Pinyin](https://en.wikipedia.org/wiki/Pinyin) @@ -26,12 +37,17 @@ In the Pinyin system there are 23 initials, 24 finals, 4 tones and a neutral ton * [Mandarin Chinese Pinyin Table](https://www.archchinese.com/chinese_pinyin.html) * [Chinese Pinyin Table ](http://www.quickmandarin.com/chinesepinyintable/) + + ## Tones * [Four tones](https://resources.allsetlearning.com/chinese/pronunciation/Four_tones) * [Neutral tone](https://resources.allsetlearning.com/chinese/pronunciation/Neutral_tone) * [Where do the tone marks go?](http://www.pinyin.info/rules/where.html) * [声调符号标在哪儿？](http://www.hwjyw.com/resource/content/2010/06/04/8183.shtml) + + ## Zhuyin + * [Bopomofo](https://en.wikipedia.org/wiki/Bopomofo) * [Zhuyin table](https://en.wikipedia.org/wiki/Zhuyin_table) diff --git a/docs/src/text_front_end.md b/docs/src/text_front_end.md index ab6441fac..071d3c3ba 100644 --- a/docs/src/text_front_end.md +++ b/docs/src/text_front_end.md @@ -1,6 +1,9 @@ # Text Front End + + ## MMSEG + * [MMSEG: A Word Identification System for Mandarin Chinese Text Based on Two Variants of the Maximum Matching Algorithm](http://technology.chtsai.org/mmseg/) * [`中文分词`简单高效的MMSeg](https://www.cnblogs.com/en-heng/p/5872308.html) * [mmseg分词算法及实现](https://blog.csdn.net/daniel_ustc/article/details/50488040) @@ -12,5 +15,7 @@ * [jkom-cloud/mmseg](https://github.com/jkom-cloud/mmseg) + ## CScanner + * [CScanner - A Chinese Lexical Scanner](http://technology.chtsai.org/cscanner/) diff --git a/requirements.txt b/requirements.txt index e3f7aeafd..fc24e50e7 100644 --- a/requirements.txt +++ b/requirements.txt @@ -8,4 +8,4 @@ SoundFile==0.9.0.post1 sox tensorboardX typeguard -yacs +yacs \ No newline at end of file diff --git a/third_party/README.md b/third_party/README.md index 836e002a8..e17040ef0 100644 --- a/third_party/README.md +++ b/third_party/README.md @@ -1,4 +1,8 @@ -* [python_kaldi_features](https://github.com/ZitengWang/python_kaldi_features) -commit: fc1bd6240c2008412ab64dc25045cd872f5e126c -ref: https://zhuanlan.zhihu.com/p/55371926 +* [python_kaldi_features](https://github.com/ZitengWang/python_kaldi_features) +commit: fc1bd6240c2008412ab64dc25045cd872f5e126c +ref: https://zhuanlan.zhihu.com/p/55371926 + +* [python-pinyin](https://github.com/mozillazg/python-pinyin.git) + commit: 55e524aa1b7b8eec3d15c5306043c6cdd5938b03 + licence: MIT diff --git a/third_party/pymmseg-cpp/README.md b/third_party/pymmseg-cpp/README.md index 6060e999b..d2afdb6e6 100644 --- a/third_party/pymmseg-cpp/README.md +++ b/third_party/pymmseg-cpp/README.md @@ -73,7 +73,7 @@ mmseg.Dictionary.load_chars('customize_chars.dic') # REQUIREMENTS: -* python 2.5+ +* python 3.7+ * g++ # INSTALLATION: