README.md

README.md

@@ -9,16 +9,22 @@ tags:
 ---
 
 ## Model description
+This model helps to classify speakers from the frequency domain representation of speech recordings, obtained via Fast Fourier Transform (FFT).
+The model is created by a 1D convolutional network with residual connections for audio classification.
 
-More information needed
+This repo contains the model for the notebook [**Speaker Recognition**](https://keras.io/examples/audio/speaker_recognition_using_cnn/).
 
-## Intended uses & limitations
+Full credits go to [**Fadi Badine**](https://twitter.com/fadibadine)
 
-More information needed
+## Dataset Used
+This model uses a [**speaker recognition dataset**](https://www.kaggle.com/kongaevans/speaker-recognition-dataset) of Kaggle
 
-## Training and evaluation data
+## Intended uses & limitations
+This should be run with `TensorFlow 2.3` or higher, or `tf-nightly`. 
+Also, The noise samples in the dataset need to be resampled to a sampling rate of 16000 Hz before using for this model so, In order to do this, you will need to have installed `ffmpg`.
 
-More information needed
+## Training and evaluation data
+During dataset preparation, the speech samples & background noise samples were sorted and categorized into 2 folders - audio & noise, and then noise samples were resampled to 16000Hz & then the background noise was added to the speech samples to augment the data. After that, the FFT of these samples was given to the model for the training & evaluation part.
 
 ## Training procedure