Update app.py

app.py

@@ -1,60 +1,23 @@
-import numpy as np
-import pickle
-import librosa
-from tensorflow.keras.models import Sequential, model_from_json
-import gradio as gr
-
-json_file = open('/content/drive/MyDrive/Project/Audio/CNN_model.json', 'r')
-loaded_model_json = json_file.read()
-json_file.close()
-loaded_model = model_from_json(loaded_model_json)
-# load weights into new model
-loaded_model.load_weights("/content/drive/MyDrive/Project/Audio/best_model1_weights.h5")
-
-
-with open('/content/drive/MyDrive/Project/Audio/scaler2.pickle', 'rb') as f:
-    scaler2 = pickle.load(f)
-
-with open('/content/drive/MyDrive/Project/Audio/encoder2.pickle', 'rb') as f:
-    encoder2 = pickle.load(f)
-
-
-def zcr(data,frame_length,hop_length):
-    zcr=librosa.feature.zero_crossing_rate(data,frame_length=frame_length,hop_length=hop_length)
-    return np.squeeze(zcr)
-def rmse(data,frame_length=2048,hop_length=512):
-    rmse=librosa.feature.rms(y=data,frame_length=frame_length,hop_length=hop_length)
-    return np.squeeze(rmse)
-def mfcc(data,sr,frame_length=2048,hop_length=512,flatten:bool=True):
-    mfcc=librosa.feature.mfcc(y=data,sr=sr)
-    return np.squeeze(mfcc.T)if not flatten else np.ravel(mfcc.T)
-
-def extract_features(data,sr=22050,frame_length=2048,hop_length=512):
-    result=np.array([])
-
-    result=np.hstack((result,
-                      zcr(data,frame_length,hop_length),
-                      rmse(data,frame_length,hop_length),
-                      mfcc(data,sr,frame_length,hop_length)
-                     ))
-    return result
-
-def get_predict_feat(path):
-    d, s_rate= librosa.load(path, duration=2.5, offset=0.6)
-    res=extract_features(d)
-    result=np.array(res)
-    result=np.reshape(result,newshape=(1,2376))
-    i_result = scaler2.transform(result)
-    final_result=np.expand_dims(i_result, axis=2)
-
-    return final_result
-
-emotions1={1:'Neutral', 2:'Calm', 3:'Happy', 4:'Sad', 5:'Angry', 6:'Fear', 7:'Disgust',8:'Surprise'}
-def prediction(path1):
-    res = get_predict_feat(path1)
-    predictions = loaded_model.predict(res)
-    predicted_class = predictions.argmax(axis=1)[0] + 1  # Convert from 0-based indexing to emotion labels
-    predicted_emotion = emotions1[predicted_class]  # Get the corresponding emotion label
-    return predicted_emotion[0]
-
-gr.Interface(fn=prediction, inputs="audio", outputs="text").launch()
+import streamlit as st
+from speechbrain.inference.interfaces import foreign_class
+
+# Initialize the classifier
+classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")
+
+def emotion(file):
+    if file is not None:
+        # Classify the file
+        out_prob, score, index, text_lab = classifier.classify_file(file.name)
+        # Display the output
+        st.write(text_lab)
+    else:
+        st.write("Please upload a file.")
+
+def main():
+    st.title("Emotion Recognition")
+    uploaded_file = st.file_uploader("Upload audio file", type=["wav"])
+    if uploaded_file is not None:
+        emotion(uploaded_file)
+
+if __name__ == "__main__":
+    main()