i am working on an android application which has a speech recognition module that works in English using google's offline speech recognition but now i want to add new language (Swahili) which is not on the list of available languages in google's offline speech recognition languages. how can i add Swahili language to it? and use it on my application?
without google supported languages you can't get them either in offline or online into voice search.
Interpretation
Since you did not specify the speech recognition you intend to use, should use google speech recognition, nor that it should work off-line, an answer to your question could be:
Solution
You could implement a pre-trained deepspeech model for the swahili language on your android.
Suggestions
Here are people working on implementing deepspeech on android. This contains an explanation on how to train your own deepspeech model. This is an example on how to use a pretrained deepspeech model in general. Here is a list of already pretrained models (I think it currently does not yet contain a Swahili example). This is where you can improve languages, Since the Swahili language is not yet started, you can subscribe here to help train the deepspeech models for that language.
Disclosure
I am not affiliated with the Deepspeech nor Mozilla.
Note
Please feel free to explain a solution you have developed if you implement one, as an additional answer to this question.
Related
I have an Android app which uses the offline Google Speech To Text engine. I want it to recognize addresses, but it tries to convert them to common words. I need some boost for a list of addresses. It's not a duplicate of Train google speech to text because I need it to work offline. It would be optimal if I add a map with phrases and a boost value in a class directly in the app.
Is that possible?
Thank you!
afaik google doesn't allow you, but you may find a way with picovoice rhino https://picovoice.ai/platform/rhino/ and here maps https://www.here.com apis. both have free tier and pretty generous.
I am developing an android app which needs Speech recognition functionality, I need app should work same as Google Translator app in which it Google translate auto detect language spoken. I checked with Microsoft Azure Speech recognition and Google Speech recognition API in both the API we need to provide language code. I searched all over but did not get any workaround or solution to achieve similar functionality. Please help.
May be I am answering late but it may help
I think problem is very large than it seems. As far as I understood you want to achieve speech-to-text and then translate text to required language.
I think using paid services of microsoft or google or amazon would be helful.
https://azure.microsoft.com/en-in/services/cognitive-services/text-analytics/
https://aws.amazon.com/comprehend/
I'm trying to create a simple application such as in the tutorial for the android vision API, only to recognize Hebrew, instead of English.
so far, from what i searched mobile vision api, and from playing around with other languages, the application recognize many Latin based languages (French, Spanish, for example) but no non-Latin character languages i tried (Chinese, Hebrew, Arabic comes to mind).
the question is, is it possible to use Google's mobile vision to read non-Latin text? if yes, how would i change my simple app to read other type of characters? and if not, what are my alternatives? i have found tessaract and Google cloud vision, but i prefer to have as little interaction with outside sources as i can, i want the app to be installed and used freely without relaying on outside engines or servers, any help and pointing in the right direction is appreciated.
Mobile vision OCR doesn't support non-latin languages.
here's a link to official documentation.
https://developers.google.com/vision/text-overview
You can use Google Cloud Vision for the required purpose but it would require internet connectivity. For now, most of the OCR supported APIs require internet connectivity, If you find any with more language support as compared to Mobile vision, please answer to your question here.
I have succesfully integrated offline speech recognition into my glass app by following these steps: link.
But I couldn´t find a possibility to change the language for recognition. Is there any or is it impossible?
(The Language files have to exist somewhere, maybe I just can replace them for another language, when there is no better possibility.
I guess it uses the files from data/data/com.google.glass.voice/files)
This question was answere here : Available Language
I saw that there is only US and EN language for now in XE 21, and Google didn't communicate about new language yet.
I am trying to build an application (which would use the Hindi language and other regional languages) to get speech voice commands.
I also need text to speech functionality in my application.
I was wondering if there was any way I could get a speech recognition library on Android? I did a quick Google search and found a couple of libraries for Hindi on the Internet but I am not sure if I can include them in my Android project. Can I?
You can use pocketsphinx for your app.It has JAVA and Python API's for capturing and recognizing speech. By default it recognizes only English. But if you provide your own Language Model (LM) and Dictionary File(.DIC), you should be able to get it working.
Not directly straightforward as using an API, but can be certainly doable
http://cmusphinx.sourceforge.net/wiki/tutorialandroid
Android does support a few languages but not very many, I think the list currently is US, Japanese and Chinese. Not Hindi yet though I would think they are working to add new language support soon.
Over on the Android Developers page they have a good example.