push root

Pushing 'Speech Emotion Recognition' portfolio project from local (cloud) to remote.

.gitattributes

@@ -32,3 +32,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+audio_clf_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+examples/example_air_conditioner.wav filter=lfs diff=lfs merge=lfs -text
+examples/example_dog_bark.wav filter=lfs diff=lfs merge=lfs -text
+examples/example_engine_idling.wav filter=lfs diff=lfs merge=lfs -text
+examples/example_jackhammer.wav filter=lfs diff=lfs merge=lfs -text
+examples/example_siren.wav filter=lfs diff=lfs merge=lfs -text
+examples/example_street_music.wav filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,59 @@
+import tensorflow as tf
+import gradio as gr
+import librosa
+import numpy as np
+import json
+
+# File Paths
+model_path = "audio_clf_model"
+encoding_path = "label_encodings.json"
+examples_path = "examples"
+
+# loading the files
+model = tf.keras.models.load_model(model_path)
+classes = json.load(open(encoding_path, "r"))
+labels = [classes[str(i)] for i in range(len(classes))]
+labels = ["negative", "positive"]#classes[target].values()
+
+def pre_processor(audio_path):
+
+  # load the audio file
+  x, sample_rate = librosa.load(audio_path)
+  
+  # feature extracting (mfccs is an aduio feature)
+  mfccs = np.mean(librosa.feature.mfcc(y=x, sr=sample_rate, n_mfcc=40).T, axis=0)
+  feature = mfccs
+  
+  return feature
+
+
+def clsf(audio_path):
+  
+  # extracting the features
+  features = pre_processor(audio_path)
+  print(len(features))
+
+  # batching the data
+  sample = np.expand_dims(features, axis=0)
+
+  # predicting
+  preds = model.predict(sample).flatten()
+  
+  # results
+  confidences = {labels[i]: np.round(float(preds[i]), 3) for i in range(len(labels))}
+
+  return confidences
+
+# GUI Component
+gui_params = {
+    "fn":clsf, 
+    "inputs":gr.Audio(source="upload", type="filepath"),
+    "outputs" : "label",
+    #live=True,
+    "examples" : examples_path
+} 
+demo = gr.Interface(**gui_params)
+
+# Launching the demo
+if __name__ == "__main__":
+    demo.launch()

audio_clf_model/fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ff7c4fb5723d5b99ce3e8e5b1a5eeca21232e36e6e29ae5cd433fd36f2a073
+size 54

audio_clf_model/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f971b6ba97c55e9406edf8f9127c08a328d0a6a9b84a381a6830b8a8571c50b8
+size 30718

audio_clf_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584ce2d364c9b19401fd5ac20c83525ab797faf12fa444bc914546d419465452
+size 280456

audio_clf_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2136eee974e2d2359724b8fe1cd5e97fd33933a728312deab1c5674c1cfd60
+size 6728254

examples/example_air_conditioner.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c943673ea7a44aa379e68d1cd098c7ff44d6db44cee9399dff5c00f8dff0a4
+size 1152080

examples/example_dog_bark.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531a6a90ce0bc598d872766a1ae783df0084e23f8be77662dffcbed9bd62fcad
+size 1152080

examples/example_engine_idling.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366e771510c21f51e72c7254f9ae14cfb53d684b77a39f19bb578d061f8e3a58
+size 2304080

examples/example_jackhammer.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a0de19f0946f0007a8c96d8473a9ba9193185a8a84fa757ea971156ed28979
+size 2304080

examples/example_siren.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b541f6f1c8e9dc208579ad45f050ac6424181539eeea33abc995d96f590d4cc
+size 1152080

examples/example_street_music.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75b3da7714ec574c58d5257dec4b87abca2f1577582b474a4b9aa5907eefd2e
+size 1058480

label_encodings.json

@@ -0,0 +1 @@
+{"0": "air_conditioner", "1": "car_horn", "2": "children_playing", "3": "dog_bark", "4": "drilling", "5": "engine_idling", "6": "gun_shot", "7": "jackhammer", "8": "siren", "9": "street_music"}

requirements.txt

@@ -0,0 +1,4 @@
+gradio==3.27.0
+librosa==0.10.0.post2
+numpy==1.22.4
+tensorflow==2.12.0