Openvino for audio processing

[MaheshKumar]

Hi 

I have a use case where

1. Identify phonenumbers/URLs in media files

2. Identify language spoken in the video

3. Identify age/region restricted content

Can OpenVINO solve all the above usecases?

[Wan_Intel]

Hi MaheshKumar,

Thanks for reaching out to us.

OpenVINO™ Toolkit is an open-source toolkit for optimizing and deploying AI inference. It converts and optimizes models trained with popular frameworks into Intermediate Representation (IR) format. IR can be used to deployed across a mix of Intel® hardware and environments, in the browser, or in the cloud.

On the other hand, Open Model Zoo from OpenVINO™ Toolkit delivers a wide variety of free, pre-trained deep learning models and demo applications that provide full application templates to help you implement deep learning in Python and C++. Models and demos are available in the Open Model Zoo GitHub repository.

Referring to your use cases, we regret to inform you that we do not have similar demo applications in our Open Model Zoo. However, you may convert and optimize your custom models trained with Supported Model Formats into IR using Model Optimizer and implement OpenVINO™ Runtime inference pipeline in your application.

For example, Speech Recognition DeepSpeech Python Demo shows Automatic Speech Recognition (ASR) using Mozilla DeepSpeech 0.8.2 model, which is one of our Public pre-trained Speech Recognition Models.

Next, Text Detection C++ Demo shows an example of using text-recognition-0012, which is one of our Intel's pre-trained Text Recognition Models to recognize printed text rotated at any angle in various environments.

Regards,

Wan

[Wan_Intel]

Hi MaheshKumar,

Thank you for your question.

If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.

Regards,

Wan