From d5c3956c944dd63f4318de1c241aaacda88748f3 Mon Sep 17 00:00:00 2001 From: Hui Zhang Date: Thu, 13 May 2021 19:20:09 +0800 Subject: [PATCH] speech text process docs (#607) * add more speech doc * fix doc path and mergify * format doc --- .mergify.yml | 6 +++--- {docs => doc}/images/multi_gpu_speedup.png | Bin {docs => doc}/images/prosody.jpeg | Bin {docs => doc}/images/tuning_error_surface.png | Bin {docs => doc}/src/asr_postprocess.md | 16 +++++++++------- {docs => doc}/src/augmentation.md | 0 {docs => doc}/src/benchmark.md | 0 {docs => doc}/src/chinese_syllable.md | 0 {docs => doc}/src/data_preparation.md | 0 doc/src/dataset.md | 15 +++++++++++++++ {docs => doc}/src/faq.md | 0 {docs => doc}/src/getting_started.md | 0 {docs => doc}/src/install.md | 0 {docs => doc}/src/ngram_lm.md | 2 -- {docs => doc}/src/reference.md | 0 {docs => doc}/src/released_model.md | 0 {docs => doc}/src/server.md | 2 +- {docs => doc}/src/speech_synthesis.md | 0 {docs => doc}/src/text_front_end.md | 11 +++++++++++ tools/Makefile | 2 +- 20 files changed, 40 insertions(+), 14 deletions(-) rename {docs => doc}/images/multi_gpu_speedup.png (100%) rename {docs => doc}/images/prosody.jpeg (100%) rename {docs => doc}/images/tuning_error_surface.png (100%) rename {docs => doc}/src/asr_postprocess.md (83%) rename {docs => doc}/src/augmentation.md (100%) rename {docs => doc}/src/benchmark.md (100%) rename {docs => doc}/src/chinese_syllable.md (100%) rename {docs => doc}/src/data_preparation.md (100%) create mode 100644 doc/src/dataset.md rename {docs => doc}/src/faq.md (100%) rename {docs => doc}/src/getting_started.md (100%) rename {docs => doc}/src/install.md (100%) rename {docs => doc}/src/ngram_lm.md (99%) rename {docs => doc}/src/reference.md (100%) rename {docs => doc}/src/released_model.md (100%) rename {docs => doc}/src/server.md (99%) rename {docs => doc}/src/speech_synthesis.md (100%) rename {docs => doc}/src/text_front_end.md (86%) diff --git a/.mergify.yml b/.mergify.yml index 255276858..5a1e1ff34 100644 --- a/.mergify.yml +++ b/.mergify.yml @@ -47,19 +47,19 @@ pull_request_rules: add: ["README"] - name: "auto add label=Documentation" conditions: - - files~=^docs/ + - files~=^doc/ actions: label: add: ["Documentation"] - name: "auto add label=CI" conditions: - - files~=^(.circleci/|ci/|.github/|.travis.yml) + - files~=^(.circleci/|ci/|.github/|.travis.yml|.travis|env.sh) actions: label: add: ["CI"] - name: "auto add label=Installation" conditions: - - files~=^(tools/|setup.py|setup.sh|env.sh|.travis) + - files~=^(tools/|setup.py|setup.sh) actions: label: add: ["Installation"] diff --git a/docs/images/multi_gpu_speedup.png b/doc/images/multi_gpu_speedup.png similarity index 100% rename from docs/images/multi_gpu_speedup.png rename to doc/images/multi_gpu_speedup.png diff --git a/docs/images/prosody.jpeg b/doc/images/prosody.jpeg similarity index 100% rename from docs/images/prosody.jpeg rename to doc/images/prosody.jpeg diff --git a/docs/images/tuning_error_surface.png b/doc/images/tuning_error_surface.png similarity index 100% rename from docs/images/tuning_error_surface.png rename to doc/images/tuning_error_surface.png diff --git a/docs/src/asr_postprocess.md b/doc/src/asr_postprocess.md similarity index 83% rename from docs/src/asr_postprocess.md rename to doc/src/asr_postprocess.md index 772bf8b25..0c84181d1 100644 --- a/docs/src/asr_postprocess.md +++ b/doc/src/asr_postprocess.md @@ -1,8 +1,9 @@ # ASR PostProcess -* Text Corrector -* Text Filter -* Add Punctuation +1. [Text Segmentation](text_front_end#text segmentation) +2. Text Corrector +3. Add Punctuation +4. Text Filter @@ -10,6 +11,7 @@ * [pycorrector](https://github.com/shibing624/pycorrector) 本项目重点解决其中的谐音、混淆音、形似字错误、中文拼音全拼、语法错误带来的纠错任务。PS：[网友源码解读](https://zhuanlan.zhihu.com/p/138981644) +* DeepCorrection [1](https://praneethbedapudi.medium.com/deepcorrection-1-sentence-segmentation-of-unpunctuated-text-a1dbc0db4e98) [2](https://praneethbedapudi.medium.com/deepcorrection2-automatic-punctuation-restoration-ac4a837d92d9) [3](https://praneethbedapudi.medium.com/deepcorrection-3-spell-correction-and-simple-grammar-correction-d033a52bc11d) [4](https://praneethbedapudi.medium.com/deepsegment-2-0-multilingual-text-segmentation-with-vector-alignment-fd76ce62194f) @@ -88,12 +90,12 @@ -## Text Filter - -* 敏感词（黄暴、涉政、违法违禁等） +## Add Punctuation +* DeepCorrection [1](https://praneethbedapudi.medium.com/deepcorrection-1-sentence-segmentation-of-unpunctuated-text-a1dbc0db4e98) [2](https://praneethbedapudi.medium.com/deepcorrection2-automatic-punctuation-restoration-ac4a837d92d9) [3](https://praneethbedapudi.medium.com/deepcorrection-3-spell-correction-and-simple-grammar-correction-d033a52bc11d) [4](https://praneethbedapudi.medium.com/deepsegment-2-0-multilingual-text-segmentation-with-vector-alignment-fd76ce62194f) +## Text Filter -## Add Punctuation +* 敏感词（黄暴、涉政、违法违禁等） diff --git a/docs/src/augmentation.md b/doc/src/augmentation.md similarity index 100% rename from docs/src/augmentation.md rename to doc/src/augmentation.md diff --git a/docs/src/benchmark.md b/doc/src/benchmark.md similarity index 100% rename from docs/src/benchmark.md rename to doc/src/benchmark.md diff --git a/docs/src/chinese_syllable.md b/doc/src/chinese_syllable.md similarity index 100% rename from docs/src/chinese_syllable.md rename to doc/src/chinese_syllable.md diff --git a/docs/src/data_preparation.md b/doc/src/data_preparation.md similarity index 100% rename from docs/src/data_preparation.md rename to doc/src/data_preparation.md diff --git a/doc/src/dataset.md b/doc/src/dataset.md new file mode 100644 index 000000000..231773a9b --- /dev/null +++ b/doc/src/dataset.md @@ -0,0 +1,15 @@ +# Dataset + +## Text + +* [Tatoeba](https://tatoeba.org/cmn) + + **Tatoeba is a collection of sentences and translations.** It's collaborative, open, free and even addictive. An open data initiative aimed at translation and speech recognition. + + + +## Speech + +* [Tatoeba](https://tatoeba.org/cmn) + + **Tatoeba is a collection of sentences and translations.** It's collaborative, open, free and even addictive. An open data initiative aimed at translation and speech recognition. diff --git a/docs/src/faq.md b/doc/src/faq.md similarity index 100% rename from docs/src/faq.md rename to doc/src/faq.md diff --git a/docs/src/getting_started.md b/doc/src/getting_started.md similarity index 100% rename from docs/src/getting_started.md rename to doc/src/getting_started.md diff --git a/docs/src/install.md b/doc/src/install.md similarity index 100% rename from docs/src/install.md rename to doc/src/install.md diff --git a/docs/src/ngram_lm.md b/doc/src/ngram_lm.md similarity index 99% rename from docs/src/ngram_lm.md rename to doc/src/ngram_lm.md index 4dc92cd9f..7bf21f894 100644 --- a/docs/src/ngram_lm.md +++ b/doc/src/ngram_lm.md @@ -86,5 +86,3 @@ Please notice that the released language models only contain Chinese simplified ``` build/bin/build_binary ./result/people2014corpus_words.arps ./result/people2014corpus_words.klm ``` - - diff --git a/docs/src/reference.md b/doc/src/reference.md similarity index 100% rename from docs/src/reference.md rename to doc/src/reference.md diff --git a/docs/src/released_model.md b/doc/src/released_model.md similarity index 100% rename from docs/src/released_model.md rename to doc/src/released_model.md diff --git a/docs/src/server.md b/doc/src/server.md similarity index 99% rename from docs/src/server.md rename to doc/src/server.md index 019ebcfa4..4918d5ebe 100644 --- a/docs/src/server.md +++ b/doc/src/server.md @@ -25,7 +25,7 @@ Then to start the client, please run this in another console: ```bash CUDA_VISIBLE_DEVICES=0 bash local/client.sh -``` +``` Now, in the client console, press the `whitespace` key, hold, and start speaking. Until finishing your utterance, release the key to let the speech-to-text results shown in the console. To quit the client, just press `ESC` key. diff --git a/docs/src/speech_synthesis.md b/doc/src/speech_synthesis.md similarity index 100% rename from docs/src/speech_synthesis.md rename to doc/src/speech_synthesis.md diff --git a/docs/src/text_front_end.md b/doc/src/text_front_end.md similarity index 86% rename from docs/src/text_front_end.md rename to doc/src/text_front_end.md index 5d53f5137..01b608591 100644 --- a/docs/src/text_front_end.md +++ b/doc/src/text_front_end.md @@ -1,5 +1,16 @@ # Text Front End + + +## Text Segmentation + +There are various libraries including some of the most popular ones like NLTK, Spacy, Stanford CoreNLP that that provide excellent, easy to use functions for sentence segmentation. + +* https://github.com/bminixhofer/nnsplit +* [DeepSegment](https://github.com/notAI-tech/deepsegment) [blog](http://bpraneeth.com/projects/deepsegment) [1](https://praneethbedapudi.medium.com/deepcorrection-1-sentence-segmentation-of-unpunctuated-text-a1dbc0db4e98) [2](https://praneethbedapudi.medium.com/deepcorrection2-automatic-punctuation-restoration-ac4a837d92d9) [3](https://praneethbedapudi.medium.com/deepcorrection-3-spell-correction-and-simple-grammar-correction-d033a52bc11d) [4](https://praneethbedapudi.medium.com/deepsegment-2-0-multilingual-text-segmentation-with-vector-alignment-fd76ce62194f) + + + ## Text Normalization(文本正则) 文本正则化 文本正则化主要是讲非标准词(NSW)进行转化，比如： diff --git a/tools/Makefile b/tools/Makefile index ef721c2b8..ea57cd2c0 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -1,4 +1,4 @@ -PYTHON:= python3.7 +PYTHON:= python3.8 .PHONY: all clean all: virtualenv