我正在尝试将自己训练好的数据加载到tesseract.js中。因为文件放在本地,所以我试着离线加载所有内容。我使用的代码如下所示:
<script src="tesseract.js"></script>
<script>
//Set the worker, core and lang to local files
(function() {
var path = (function() { //absolute path
var pathArray = window.location.pathname.split( '/' );
pathArray.pop(); //Remove the last ("**.html")
return window.location.origin + pathArray.join("/");
})();
console.log(path);
window.Tesseract = Tesseract.create({
workerPath: path + '/worker.js',
//langPath: path + '/traineddata/',
corePath: path + '/index.js',
});
})();
</script>
<script>
function recognizeFile(file){
document.querySelector("#log").innerHTML = ''
Tesseract.recognize(file, {
lang: document.querySelector('#langsel').value
})
.progress(function(packet){
console.info(packet)
progressUpdate(packet)
})
.then(function(data){
console.log(data)
progressUpdate({ status: 'done', data: data })
})
}
</script>如果没有设置langPath,上面的代码可以正常工作,但当我将langPath指向本地文件夹时,Tesseract无法加载任何内容,并显示以下错误:
Failed loading language 'eng'
Tesseract couldn't load any languages!..。
AdaptedTemplates != NULL:Error:Assert failed:in file ../classify/adaptmatch.cpp, line 190
SCRIPT0: abort() at Error
at Na (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:36:24)
at ka (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:511:83)
at Module.de._abort (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:377:166)
at $L (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:387:55709)
at jpa (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:392:22274)
at lT (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:391:80568)
at mT (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:391:80698)
at BS (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:391:69009)
at bP (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:387:110094)
at jT (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:391:80280)
at RJ (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:387:19088)
at QJ (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:387:17789)
at zI (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:403:90852)
at tw (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:401:49079)
at rw (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:401:48155)
at lw (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:401:39071)
at _v (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:401:22565)
at aw (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:401:24925)
at cw (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:401:27237)
at oj (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:386:24689)
at Og (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:386:10421)
at $.prototype.Recognize (file:///C:/Users/user/Downloads/tesseract.js-master/dist/index.js:558:379)
at Anonymous function (file:///C:/Users/user/Downloads/tesseract.js-master/dist/worker.js:8814:9)
at Anonymous function (file:///C:/Users/user/Downloads/tesseract.js-master/dist/worker.js:8786:9)
at xhr.onerror (file:///C:/Users/user/Downloads/tesseract.js-master/dist/worker.js:8429:9)
If this abort() is unexpected, build with -s ASSERTIONS=1 which can give more information.
index.js (8,1)我将eng.traineddata和eng.traineddata.gz都放在了/traineddata文件夹中,因为明显地跳过了ungzip过程。我是不是忽略了什么?任何帮助都是非常感谢的。
发布于 2018-04-26 15:38:58
我知道这是一个古老的问题,但最近我需要在我的一个项目中使用Tesseract.js。我需要在本地加载数据文件,所以这是我所做的。
而不是创建一个新的工人。我修改了可用的默认worker选项。所以我没有使用Tesseract.createWorker,而是直接设置了路径,而使用了recognize。
Tesseract.workerOptions.langPath =
window.location.origin // take protocol://domain.com part
+ "/scripts/tesseract/dist/"; // location of data files
//you could set core and worker paths too but I didn't need it
Tesseract.workerOptions.workerPath =
window.location.origin // take protocol://domain.com part
+ "/scripts/tesseract/dist/worker.js"; // location of worker.js
//you could set core and worker paths too but I didn't need it
Tesseract.workerOptions.corePath =
window.location.origin // take protocol://domain.com part
+ "/scripts/tesseract/dist/index.js"; // location of index.js
//example lang path would be protocol://domain.com/scripts/tesseract/dist/通过这样做,我保留了指向默认CDN的工作路径和核心路径不变。
PS:当使用本地worker.js和core.js路径时,我在worker.js中的postMessage()上遇到未捕获的错误。这就是为什么我只对langData使用本地路径的原因。我仍然不知道如何修复它,也不知道为什么会发生这种情况。但是,您可以关注本期 和
发布于 2018-11-10 05:11:41
我通过从tesseract.js-core 0.1.0获取corePath文件解决了这个问题
window.Tesseract = Tesseract.create({
workerPath: window.location.origin + "/tesseract/worker.js", //tesseract.js-1.0.10
langPath: window.location.origin + "/tesseract/",
corePath: window.location.origin + "/tesseract/index.js", //tesseract.js-core-0.1.0
});和来自https://github.com/naptha/tessdata/tree/gh-pages/3.02的语言gz
https://stackoverflow.com/questions/44450010
复制相似问题