first commit

README-Copy1.md

@@ -0,0 +1,13 @@
+---
+title: UbranSounds8K
+emoji: 🏃
+colorFrom: gray
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.0.3
+app_file: app.py
+pinned: false
+license: gpl
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

article.md

@@ -0,0 +1,15 @@
+
+Dataset for this - https://urbansounddataset.weebly.com/urbansound8k.html
+
+Classical approaches on this dataset as of 2019 - https://www.researchgate.net/publication/335862311_Evaluation_of_Classical_Machine_Learning_Techniques_towards_Urban_Sound_Recognition_on_Embedded_Systems 
+
+
+
+#Fast.ai was used to train this classifier with a Resnet34 vision learner with 3 epochs.  Audio files converted to Mel Spectrograms that perform better in general for visual transformations of such audio files.
+
+epoch	train_loss	valid_loss	accuracy	time
+0	1.462791	0.710250	0.775487	01:12
+epoch	train_loss	valid_loss	accuracy	time
+0	0.600056	0.309964	0.892325	00:40
+1	0.260431	0.200901	0.945017	00:39
+2	0.090158	0.164748	0.950745	00:40

export.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973aa561e19c98eea4faf8ddf1a0a1622c4e70b9a0879f266fb5d92e3747a4e4
+size 87601195

requirements.txt

@@ -0,0 +1,5 @@
+fastai==2.6.0
+gradio==2.9.4
+librosa==0.9.1
+matplotlib==3.5.0
+huggingface_hub