initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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
+finalized_rf.sav filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,103 @@
+import gradio as gr
+import wave
+import matplotlib.pyplot as plt
+import numpy as np
+from extract_features import *
+import pickle
+import soundfile 
+import librosa
+
+classifier = pickle.load(open('finalized_rf.sav', 'rb'))
+
+def emotion_predict(input):
+  input_features = extract_feature(input, mfcc=True, chroma=True, mel=True, contrast=True, tonnetz=True)
+  rf_prediction = classifier.predict(input_features.reshape(1,-1))
+  if rf_prediction == 'happy':
+    return 'Happy 😎'
+  elif rf_prediction == 'neutral':
+    return 'Neutral 😐'
+  elif rf_prediction == 'sad':
+    return 'Sad 😢'
+  else:
+    return 'Angry 😤'
+  
+
+def plot_fig(input):
+  wav = wave.open(input, 'r')
+
+  raw = wav.readframes(-1)
+  raw = np.frombuffer(raw, "int16")
+  sampleRate = wav.getframerate()
+
+  Time = np.linspace(0, len(raw)/sampleRate, num=len(raw))
+
+  fig = plt.figure()
+
+  plt.rcParams["figure.figsize"] = (50,15)
+
+  plt.title("Waveform Of the Audio", fontsize=25)
+
+  plt.xticks(fontsize=15)
+
+  plt.yticks(fontsize=15)
+
+  plt.ylabel("Amplitude", fontsize=25)
+
+  plt.plot(Time, raw, color='red')
+
+  return fig
+
+
+with gr.Blocks() as app:
+  gr.Markdown(
+        """
+    # Speech Emotion Detector 🎵😍
+    This application classifies inputted audio 🔊 according to the verbal emotion into four categories:
+    1. Happy 😎
+    2. Neutral 😐
+    3. Sad 😢
+    4. Angry 😤
+    """
+  )
+  with gr.Tab("Record Audio"):
+    record_input = gr.Audio(source="microphone", type="filepath")
+        
+    with gr.Accordion("Audio Visualization", open=False):
+      gr.Markdown(
+          """
+      ### Visualization will work only after Audio has been submitted
+      """
+      )    
+      plot_record = gr.Button("Display Audio Signal")
+      plot_record_c = gr.Plot(label='Waveform Of the Audio')
+    
+    record_button = gr.Button("Detect Emotion")
+    record_output = gr.Text(label = 'Emotion Detected')
+
+  with gr.Tab("Upload Audio File"):
+    gr.Markdown(
+        """
+    ## Uploaded Audio should be of .wav format
+    """
+    )
+
+    upload_input = gr.Audio(type="filepath")
+
+    with gr.Accordion("Audio Visualization", open=False):
+      gr.Markdown(
+          """
+      ### Visualization will work only after Audio has been submitted
+      """
+      )
+      plot_upload = gr.Button("Display Audio Signal")
+      plot_upload_c = gr.Plot(label='Waveform Of the Audio')
+
+    upload_button = gr.Button("Detect Emotion")
+    upload_output = gr.Text(label = 'Emotion Detected')
+    
+  record_button.click(emotion_predict, inputs=record_input, outputs=record_output)
+  upload_button.click(emotion_predict, inputs=upload_input, outputs=upload_output)
+  plot_record.click(plot_fig, inputs=record_input, outputs=plot_record_c)
+  plot_upload.click(plot_fig, inputs=upload_input, outputs=plot_upload_c)
+
+app.launch()

extract_features.py

@@ -0,0 +1,33 @@
+import numpy as np
+import soundfile
+import librosa
+
+def extract_feature(file_name, **kwargs):
+    
+    chroma = kwargs.get("chroma")
+    contrast = kwargs.get("contrast")
+    mfcc = kwargs.get("mfcc")
+    mel = kwargs.get("mel")
+    tonnetz = kwargs.get("tonnetz")
+    
+    with soundfile.SoundFile(file_name) as audio_clip:
+        X = audio_clip.read(dtype="float32")
+        sound_fourier = np.abs(librosa.stft(X))   # Conducting short time fourier transform of audio clip
+        result = np.array([])
+        
+        if mfcc:
+            mfccs = np.mean(librosa.feature.mfcc(y=X, sr=audio_clip.samplerate, n_mfcc=40).T, axis=0)
+            result = np.hstack((result, mfccs))
+        if chroma:
+            chroma = np.mean(librosa.feature.chroma_stft(S=sound_fourier, sr=audio_clip.samplerate).T, axis=0)
+            result = np.hstack((result, chroma))
+        if mel:
+            mel = np.mean(librosa.feature.melspectrogram(X, sr=audio_clip.samplerate).T, axis=0)
+            result = np.hstack((result, mel))
+        if contrast:
+            contrast = np.mean(librosa.feature.spectral_contrast(S=sound_fourier, sr=audio_clip.samplerate).T, axis=0)
+            result = np.hstack((result, contrast))
+        if tonnetz:
+            tonnetz = np.mean(librosa.feature.tonnetz(y=librosa.effects.harmonic(X), sr=audio_clip.samplerate).T, axis=0)
+            result = np.hstack((result, tonnetz))
+    return result

finalized_rf.sav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf37e379f462a4f0e936c39a69aee28e4941c4de46f2e3308711f27042fb514
+size 3096321