Gravitational waves are ripples in the fabric of space-time that travel at the speed of light. The detection of gravitational waves by LIGO is a major breakthrough in the field of astronomy. Deep Learning has revolutionized many industries including health care, finance and education. Deep Learning techniques have also been explored for detection of gravitational waves to overcome the drawbacks of traditional matched filtering method. However, in several researches, the training phase of neural network is very time consuming and hardware devices with large memory are required for the task. In order to reduce the extensive amount of hardware resources and time required in training a neural network for detecting gravitational waves, we made SpecGrav. We use 2D Convolutional Neural Network and spectrograms of gravitational waves embedded in noise to detect gravitational waves from binary black hole merger and binary neutron star merger. The training phase of our neural network was of about just 19 minutes on a 2GB GPU. INTRODUCTION: On 14 September 2015, LIGO detectors at Hanford and Livingston detected gravitational waves for the first time from the merger of two black holes. This event is named GW150914. It is a Nobel Prize winning discovery that substantiates Einstein’s general theory of relativity. The sources of gravitational waves detected so far are compact binary coalesces, namely binary neutron star (BNS) merger and binary black hole (BBH) merger. Gravitational waves carry information of their origin with them which includes source masses, spins, distance of the sources from us and much more. They help us understand the objects that are billions of light years far from us, which we could never reach. But when these waves reach us their amplitude can be smaller than the diameter of a proton. Therefore, highly sensitive instruments are required to detect them. To find gravitational waves in detector noise is a meticulous task. Also, in case of binary neutron star merger, gravitational waves are accompanied by their electromagnetic counterparts. Therefore, rapid detection of gravitational waves in such events is very crucial in order to detect various other remnants of the event like electromagnetic signals and gamma-ray bursts. The method currently used by LIGO for the detection of gravitational waves is Matched Filtering. This method is very time consuming and computationally very expensive. Hence, to overcome the drawbacks of matched filtering many researchers have turned towards deep learning for detection of gravitational waves. Neural networks are trained on a sufficiently large dataset and once trained they can predict output in seconds. However, one disadvantage of many deep learning techniques used so far for the detection of gravitational waves is that their training phase is very time consuming and requires large memory hardware devices. In this paper, we present a way to reduce the time and resources required for training deep neural network for realtime detection of gravitational waves from binary neutron star (BNS) merger and binary black hole (BBH) merger. We use 2D Convolutional Neutral Network and spectrograms of GW signals embedded in noise for this task. A spectrogram is an image showing the variation of frequency of a signal with time. Using spectrograms instead of time series considerably reduces the size of our dataset.