speech recognition and human activity observation from a webcam -- 2

Hi, Greetings for the day! We are a team of passionate Machine Learning Engineers based in Mumbai, India, who have developed and deployed complex AI solutions using Machine Learning and Computer Vision. Upon going through the specified requirements, we believe that we are a good fit for this project. We can help you out with your algorithm and train a model, along with the best optimization techniques, either using any open-source repository or built using any architecture reference! We have also successfully built and trained various general as well as client specific image classification, image recognition as well as object detection, using prebuilt as well as customized state of the art architectures such as Resnet, MobileNet, YOLO, SSD, RetinaNet. Some of our projects include Face Mask Detection, Social Distancing Monitoring, Industrial Machinery Defect Detection, Industrial Safety Kit Detection, Root Cause Analysis and more. Our AI/ML tech-stack includes Python, Tensorflow, PyTorch, Keras, OpenCV, GCP, AWS, FastAPI, Flask, Django and more. We have relevant and significant experience in Keras, TensorFlow and OpenCV. Please checkout our AI/ML portfolio - freelancer.in/u/iPingDataLabsLLP We approach our each client with the intent of a long term relationship. Can we connect over chat and discuss a plan of action? Regards, iPing Data Labs

Hello dear client. I am very interested in your project. I have experience implementing existing machine learning and AI models and I have also experience creating new machine learning models (for which I have evidence published in research journals). Please let me know more details if you have more specific requirements. I could build your application with Python, or possibly other languages depending on your requirements. I would also need to know if it is for desktop or web application or mobile application. Broadly speaking I can think of two different modules: one for human activity recognition based on the webcam video input and another for the voice recognition based on the audio input from the webcam. Once the activity or voice is recognized, the time can also be extracted and saved where you require it (hard disk, database, etc). I would love working on your project. Please let me know more details, specially how big the requirements are in order to provide you an estimated deadline and if you have already a specific deadline. Thank you.