Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+speech-emotion-recognition.hdf5 filter=lfs diff=lfs merge=lfs -text

MT.py

@@ -0,0 +1,34 @@
+import random
+import spotipy
+from spotipy.oauth2 import SpotifyClientCredentials
+
+# Authenticate with Spotify API
+client_id = '471e06ff0a13445095909029b18c265c'
+client_secret = 'c0f56895d29f434cbeac4309d0b42d05'
+client_credentials_manager = SpotifyClientCredentials(client_id=client_id, client_secret=client_secret)
+sp = spotipy.Spotify(client_credentials_manager=client_credentials_manager)
+
+def search_song_by_emotion(emotion):
+    # Define a mapping of emotions to search keywords
+    emotion_keywords = {
+        "neutral": ["raga des sarangi", "raga malkauns", "raga bhairav", "raga rageshri"],
+        "surprise": ["raag hameer", "raag kedar", "raga puriya"],
+        "fear": ["raag bilahari", "raag purvi",  "raag shudh kalyan", "raag miya ki malhar"],
+        "sad": ["raag yaman sitar", "raga hameer","raga shyam kalyan"],
+        "angry": ["raag jaijaiwanti", "raag bhairavi", "raga puriya", "raag kafi"],
+        "happy": ["raga hamsadhwani sarod", "raga khamaj", "raga bhupali", "raga bahar"],
+        "disgust": ["raga khamaj", "raga bilaskhani todi", "raga shudh kalyan", "raga puriya"]
+    }
+
+    # Search for playlists based on the emotion keywords
+    keywords = emotion_keywords.get(emotion.lower(), [])
+    if keywords:
+        keywords = random.choice(keywords)
+        results = sp.search(q=f"track:{keywords}", type="track", limit=1)
+        tracks = results["tracks"]["items"]
+
+        # Extract song previews from the playlists
+        if tracks:
+          preview_url = tracks[0]["preview_url"]
+          return preview_url
+    return None

SER.py

@@ -0,0 +1,115 @@
+import pandas as pd
+import numpy as np
+
+import librosa
+
+import sklearn
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.model_selection import train_test_split
+
+import tensorflow as tf
+from keras.models import load_model
+
+import pickle 
+
+sample_rate = 22050
+
+def noise(data):
+    noise_value = 0.015 * np.random.uniform() * np.amax(data)
+    data = data + noise_value * np.random.normal(size=data.shape[0])
+    return data
+
+def stretch(data, rate=0.8):
+    return librosa.effects.time_stretch(data, rate=rate)
+
+def shift(data):
+    shift_range = int(np.random.uniform(low=-5, high=5) * 1000)
+    return np.roll(data, shift_range)
+
+def pitch(data,sampling_rate,pitch_factor=0.7):
+    return librosa.effects.pitch_shift(data,sr=sampling_rate, n_steps=pitch_factor)
+
+def extract_process(data):
+
+    sample_rate = 22050
+    output_result = np.array([])
+    mean_zero = np.mean(librosa.feature.zero_crossing_rate(y=data).T,axis=0)
+    output_result = np.hstack((output_result,mean_zero))
+
+    stft_out = np.abs(librosa.stft(data))
+    chroma_stft = np.mean(librosa.feature.chroma_stft(S=stft_out,sr=sample_rate).T,axis=0)
+    output_result = np.hstack((output_result,chroma_stft))
+
+    mfcc_out = np.mean(librosa.feature.mfcc(y=data,sr=sample_rate).T,axis=0)
+    output_result = np.hstack((output_result,mfcc_out))
+
+    root_mean_out = np.mean(librosa.feature.rms(y=data).T,axis=0)
+    output_result = np.hstack((output_result,root_mean_out))
+
+    mel_spectogram = np.mean(librosa.feature.melspectrogram(y=data,sr=sample_rate).T,axis=0)
+    output_result = np.hstack((output_result,mel_spectogram))
+
+    return output_result
+
+def export_process(path):
+
+    data,sample_rate = librosa.load(path,duration=2.5,offset=1)
+
+    output_1 = extract_process(data)
+    result = np.array(output_1)
+
+    noise_out = noise(data)
+    output_2 = extract_process(noise_out)
+    result = np.vstack((result,output_2))
+
+    new_out = stretch(data)
+    strectch_pitch = pitch(new_out,sample_rate)
+    output_3 = extract_process(strectch_pitch)
+    result = np.vstack((result,output_3))
+
+    return result
+
+# Load X_train from Google Drive
+with open('X_train.pkl', 'rb') as f:
+    X_train = pickle.load(f)
+
+# Load X_train from Google Drive
+with open('Y_train.pkl', 'rb') as f:
+    Y_train = pickle.load(f)
+
+Features = pd.DataFrame(X_train)
+Features['labels'] = Y_train
+
+X = Features.iloc[: ,:-1].values
+Y = Features['labels'].values
+
+encoder_label = OneHotEncoder()
+Y = encoder_label.fit_transform(np.array(Y).reshape(-1,1)).toarray()
+
+x_train, x_test, y_train, y_test = train_test_split(X, Y, train_size=0.9, random_state=42, shuffle=True)
+
+scaler_data = StandardScaler()
+x_train = scaler_data.fit_transform(x_train)
+x_test = scaler_data.transform(x_test)
+
+def preprocess_audio(audio):
+    #data, sample_rate = librosa.load(audio, duration=2.5, offset=0.6)
+    features = export_process(audio)
+    features = scaler_data.transform(features)
+    return np.expand_dims(features, axis=2)
+
+# Function to predict emotion from preprocessed audio
+def predict_emotion(preprocessed_audio):
+    model = load_model('speech-emotion-recognition.hdf5')
+    prediction = model.predict(preprocessed_audio)
+    predicted_emotion = encoder_label.inverse_transform(prediction)
+    return predicted_emotion[0]
+
+# Live emotion recognition
+def live_emotion_recognition(audio_path):
+    # Preprocess live audio
+    preprocessed_audio = preprocess_audio(audio_path)
+    # Predict emotion
+    predicted_emotion = predict_emotion(preprocessed_audio)
+    #print("Predicted Emotion:", predicted_emotion)
+    return predicted_emotion[0]

X_train.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca0b38da847556205b8092899f4472153bf65fd3af95055d5df4c51720c44e2
+size 11165240

Y_train.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade5a4397190642531e4d909cb18b54aa5f12cae4b587483f8190576ac01c8b0
+size 48108

speech-emotion-recognition.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9efa37a959fbc465d3a96912383c28cef9a35c3d0cb2065abda86f58c13ee32
+size 6747280