Update README.md

README.md

@@ -51,3 +51,24 @@ Sample datasets can be chosen as circles, moons, or scurve.
 ![cnf-viz](https://user-images.githubusercontent.com/72425253/126124351-44e00438-055e-4b1c-90ee-758a545dd602.gif)
 ![cnf-viz](https://user-images.githubusercontent.com/72425253/126124648-dcb3f8f4-396a-447c-96cf-f9304377fa48.gif)
 ![cnf-viz](https://user-images.githubusercontent.com/72425253/126127269-4c02ee6a-a9a3-4b9f-b380-f8669f58872b.gif)
+
+# Bird Call generation Score SDE 
+
+This are the codes for the bird call generation score sde model. 
+
+<code>core-sde-sampler.py</code> will execute the sampler. The sampler uses pretrained weight to generate bird calls.  
+
+For using different sample generation parameters,
+```bash
+python main.py --sigma=25 --num_steps=500 --signal_to_noise_ratio=0.10 --etol=1e-5 --sample_batch_size = 128 --sample_no = 47
+``` 
+In order to generate the audios, these dependencies are required,
+
+```bash 
+pip install librosa
+pip install soundfile
+```
+In order to train the model from scratch, please generate the dataset using this [link](www.kaggle.com/ibraheemmoosa/birdsong-spectogram-generation). The dataset is generated in kaggle. Therefore, during training your username and api key is required in the specified section. 
+```bash
+python main.py --sigma=35 --n_epochs=1000 --batch_size=512 --lr=1e-3 --num_steps=500 --signal_to_noise_ratio=0.15 --etol=1e-5 --sample_batch_size = 64 --sample_no = 23
+```