I think it's needless to point out that you do realize that [hanzi --> pinyin] is not a straightforward function, because of the ambiguous relation of characters and pronunciation (多音字).
Character by character rendering is a very simple way, but will leave you with many false pinyin syllables and/or multiple options.This site gives all the different pinyins ...
There are many online OCR input websites. For example:
http://www.yibizi.com/html5/ (neat and fast, without ads, but seems only working inside China)
I strongly suggest you install a client software rather than using a website because many websites are full of ads. And many of them are only working in some particular browsers, like infamous IE series.
Well, actually many input tools like Sogou and MSpinyin have already had such functions.
I don't know a lot of the database you referred to, but I guess it is the database of China's household registration department. I guess, in that system, not only do you need to register these antediluvian names, but you also have to select these obscure characters ...
I found the Pleco app manages to do this task using the (free) option Screen Reader:
For example, browsing online in a website:
If we press on the button
, the app recognizes the characters and pressing on any character gives the pinyin and the translation:
You can even listen to the selected character or the whole text with the corresponding buttons: .
There are several ways to look up characters without knowing their pronunciation.
In printed dictionaries, you need to identify the character's radical (or at least one of the character's radical components), consult the dictionary's radical index (where characters with that radical will be ordered by number of strokes) and thus find the character's ...
After some research into this I found this website: http://docs.bosonnlp.com/ner.html. If you set up an account on their website, you can use their NER functionality (because you need an API Token. I tried their Python example
NER_URL = 'http://api.bosonnlp.com/ner/analysis'
s = ['对于该小孩是不是郑尚金的孩子，目前已做亲子鉴定，结果还没出来，'
If you want to understand the structure of addresses, this Phonemica post is a good place to start. Turns out it's complicated.
Roughly speaking, it's a hierarchical system working from the top down, from left to right. So, country (optional), province, prefecture level city, small town, district, etc. Unfortunately the levels are not ...
You can simply use Google translate input method. They have a handwriting recognition pad.
Let's see a screenshot:
See how it works in action. (dial down the volume first)
Bonus (so you want to learn how to type Chinese):
Video: How to type Chinese using Google translate?
Video: How to type Chinese using Windows built-in input method?
2-1. Setting ...
try to use "Sougou pinyin for Windows(exe)",
for Linux use "Sougou pinyin for 32bit Linux(deb)"
or "Sougou pinyin for 64bit Linux(deb)"
or "Sougou pinyin for Mac OS(dmg)"
or "Sougou pinyin for Android (apk)"
First, there is no legal source to download both of them.
More specific, they're content of copyright. The Commercial Press has made great effort to ban online version to protect its interest. So you can hardly find the website which is providing PDF or other format.
However, there's another way, but you'd pay a little money(~$2). Visit the greatest ...
You can install ibus and ibus-pinyin (there's also google pinyin but I personally prefer ibus-pinyin) or scim. Scim is more the historical software, but ibus is definitely better.
You will probably have to restart (!), but then there's about no configuration: at most, you learn the shortcuts to switch between input methods.
Many of the keyboards available have loads of bloatware, ads and require an incredible amount of permissions on your phone. They sometimes come in installed sizes of nearly 100 Megabytes.
This is why I suggest another option: Multiling O Keyboard. It
needs next to zero permissions
is free of cost and free of ads (albeit not open source)
You're right about the company. It's full name is 科大讯飞. 科大is short for 中国科学技术大学(University of Science and Technology of China)，my Alma mater!--this company is founded by several alumni in cooperation with the university.
TTS is not difficult for 科大讯飞, and they put their effort more on speech-to-text engine. But they have open source packages for both TTS ...
Taiwan, traditional characters, csv
外国地名译名手册 / Mainland
Mainland, simplified characters, but can only find scanned copies online
There certainly have been approaches like the one you described. There's a relatively early prototype by Hobby and Goan (http://www.tug.org/TUGboat/Articles/tb05-2/tb10hobby.pdf) for a Chinese font defined in MetaFont (TeX's font description language) and another later attempt by a guy named Laguna (https://www.tug.org/TUGboat/tb26-2/laguna.pdf). There's a ...
The question you are asking is basically, "how do I shape ideographic description sequences (IDS's)"? Text shaping is how the Arabic word خط العائلة becomes خط العائلة.
It is technically possible. I am working on a proof-of-concept that can shape any IDS with a recursion depth of 2 or less. The recursion depth is needed due to limits of ...
This doesn't work with all texts but it should provide a 100% grab for supported texts.
You can use parameters to find proper name marks throughout texts:
In Chinese writing, a proper name mark (Simplified Chinese: 专名号, zhuānmínghào; Traditional Chinese: 專名號) is an underline used to mark proper names, such as the names of people, places, dynasties, ...
Ok, I could have gotten this done a lot sooner but I'm a lazy prick, here it is:
Wasn't what I was originally planning on doing when I got off work but here it is. I searched up "100 most basic Chinese characters" and put those through and it pumped out 1500 unique words. I might work on this further in the future but for now I don't event want to look at ...