Mozilla 實做百度發表的 Speech-To-Text 引擎 Deep Speech

Hacker News 上看到 MozillaGitHub 上的 mozilla/DeepSpeech 這個專案,用 TensorFlow 實做了百度的「Deep Speech: Scaling up end-to-end speech recognition」論文:

A TensorFlow implementation of Baidu's DeepSpeech architecture

語音轉文字的方案,Mozilla 開專案實做出來了...

這程式碼需要安裝 Git Large File Storage 才能完整下載包含訓練資料的部份:

Manually install Git Large File Storage, then clone the repository normally:
git clone https://github.com/mozilla/DeepSpeech

而目前已經有的資料來自於 Mozilla 另外一個專案「Common Voice」:

The Common Voice project is Mozilla's initiative to help teach machines how real people speak.

Common Voice 這個專案目前只有英文,網頁上就可以參與 validation 過程...

AWS 的翻譯服務:Amazon Translate

Google 的應該是做的最早的,MicrosoftMicrosoft Translator Text API 也出來一陣子了,而 AWS 在這次 re:Invent 推出了自家的翻譯服務 Amazon Translate:「Introducing Amazon Translate – Real-time Language Translation」。

目前還在 Preview,需要申請才能用,不過價目表「Amazon Translate Pricing」已經先出來了 (畢竟已經有競爭對手,可以參考他們的價錢):

Sign up for the Amazon Translate preview today and try the translation service. Learn more about the service by checking out the preview product page or reviewing the technical guides provided in the AWS documentation.

然後目前支援的語言有這些,都是對英文轉換:

At Preview, Amazon Translate supports translation between English and any of the following languages: Arabic, Chinese (Simplified), French, German, Portuguese, and Spanish. Support for more languages is coming soon.

英文母語的人學習外語所需的時間

這個報導蠻有趣的:「A Map Showing How Much Time It Takes to Learn Foreign Languages: From Easiest to Hardest」。

文章裡分成這幾種:(扣除已經是母語的英語,Category 0)

  • Category I: 23-24 weeks (575-600 hours) Languages closely related to English
  • Category II: 30 weeks (750 hours) Languages similar to English
  • Category III: 36 weeks (900 hours) Languages with linguistic and/or cultural differences from English
  • Category IV: 44 weeks (1100 hours) Languages with significant linguistic and/or cultural differences from English
  • Category V: 88 weeks (2200 hours) Languages which are exceptionally difficult for native English speakers

其中時間最長的這部份引用一下:

Arabic
Cantonese (Chinese)
Mandarin (Chinese)
*Japanese
Korean
* Usually more difficult than other languages in the same category.

字母在單字裡的位置分佈

是一篇老文章了... (2014 年的文章,最近從其他地方提起)

這邊講的是英文,不過同樣方式也可以拿來分析其他語言:「The distribution of letters in English words」,原始文章在「Graphing the distribution of English letters towards the beginning, middle or end of words」。

原文有描述他的資料分析來源:

The data is from the entire Brown corpus in the Natural Language Toolkit. It's a smaller and out-of-date corpus, but it's open source and easy to obtain. I repeated the analysis with COHA, the Corpus of Historical American English, a well-curated, proprietary data set from Brigham Young University for which I have a license, and the only differences were in rare letters like "z" or "x".

用程式自動同步字幕與聲音

Hacker News 上看到的專案,readbeyond/aeneas

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment).

馬上想到的是... 這根本就是字幕組的福音 XDDD

支援的語言:

Confirmed working on 38 languages: AFR, ARA, BUL, CAT, CYM, CES, DAN, DEU, ELL, ENG, EPO, EST, FAS, FIN, FRA, GLE, GRC, HRV, HUN, ISL, ITA, JPN, LAT, LAV, LIT, NLD, NOR, RON, RUS, POL, POR, SLK, SPA, SRP, SWA, SWE, TUR, UKR

除了 ENG 以外,有 JPN... XD

Mac 上的 Cleartext

看到 Mac 上的「Cleartext」這個軟體:

A text editor that only allows the 1,000 most common words in English

限制你使用比較簡單的英文,這樣可以讓讀的人比較容易了解 (尤其是非母語的人)。

有種跟 Simple English Wikipedia 的想法很像的感覺:

The project uses around 2,000 common English words, and is based on Basic English, an 850-word auxiliary international language created by Charles Kay Ogden in the 1920s.

另外還有提供 Trump mode XDDD:

Trained with a few of Trump's best known speeches, the app is now ready to help you write like a billionaire.

這好壞 XDDD

用 Spoofs Lang 更改網站偵測的預設語系...

因為 redports.org 一直連不上,寫信給網站管理者後才發現是 Trac 沒處理好 non-en 語系的部份,所以得先在 client workaround。(管理者說他有空的時候會去看看...)

Google Chrome 上可以用 Spoofs Lang 更改瀏覽器送出的 Accept-Language 欄位,進而達到修改網站偵測的預設語系...

除了 redports.org 以外,也順便把 php.net 系列的網站都改成英文語系了。