Javascript 在tesseract.js中加载脱机lang数据

Javascript 在tesseract.js中加载脱机lang数据,javascript,tesseract.js,Javascript,Tesseract.js,我正在尝试将自己经过训练的数据加载到tesseract.js。由于文件放在本地,我尝试脱机加载所有内容。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 =

我正在尝试将自己经过训练的数据加载到tesseract.js。由于文件放在本地,我尝试脱机加载所有内容。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>


我在/traineddata文件夹中有eng.traineddata和eng.traineddata.gz,因为显然取消压缩过程被跳过。有什么我忽略的吗?感谢您的帮助

我知道这个问题很老,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,所以这里是我所做的

而不是创建一个新的工作者。我修改了可用的默认辅助选项。因此,我没有使用Tesseract.createWorker,而是直接设置路径并使用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,我保持了指向默认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()上发现了未捕获的错误。这就是为什么我只对langData使用本地路径。我仍然不知道如何修复它,也不知道它为什么会发生。但是,您可以关注这个问题,我通过从


和来自

的语言gz嗨,你找到了解决问题的方法吗?我也面临着类似的问题。这在任何意义上都不是一个解决方案,但我将数据转换为blob并将其放入js文件中以加载它。所以tesseract索引文件是否能够读取该blob文件并给出正确的输出?无论如何,我能够在本地加载语言文件,它现在对我来说工作正常。
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)
 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/
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
});