Welcome to ImageAI Forum

The ImageAI forum is a community for developers, researchers, students and collaborators to meet, discuss and share on the ImageAI project, ask questions, make suggestions, showcase projects build on ImageAI and more.

Feel free to join, post and participate in discussions.


I need to process some of my images captured by camera and then convert it into voice msg for telling what kind of object is found. kindly guide me how can i do this?
I have try your 5 line code for image recognition on anaconda software at jupyter notebook
but it is not working. It is giving an error:
FileNotFoundError: [WinError 3] The system cannot find the path specified: ‘idenprof\train’

@fatima The error you are having with your code in Jupyter notebook is a filepath problem. Ensure the target folder is in the right path as specified in your code.

As per generating voice message for your model’s result, you need to use a Speech Synthesis model to achieve this.

NB: ImageAI doesn’t support speech.

1 Like

From where i can get help related to speech synthesis

1 Like

You can use WaveGlow from NVIDIA