Added the modules and the required models

audio_splitting.py

@@ -0,0 +1,37 @@
+import pydub
+from pydub import AudioSegment
+import feature_extraction
+import io
+def split_audio(uploaded_file):
+    # Load your audio file
+    # audio = AudioSegment.from_file("classical.00000.wav", format="wav")
+    audio = AudioSegment.from_file(uploaded_file,)
+    # Define the duration of each segment in milliseconds (3 seconds)
+    segment_duration = 3 * 1000  # 3 seconds in milliseconds
+
+    # Check the total duration of the audio
+    audio_duration = len(audio)
+
+    # Check if the audio is shorter than 1 minute and 3 seconds
+    if audio_duration < 63 * 1000:
+        # If it's shorter, take audio from 0 to 3 seconds
+        segment = audio[:segment_duration]
+    else:
+        # If it's longer, take audio from 1 minute to 1 minute 3 seconds
+        start_time = 60 * 1000  # 1 minute in milliseconds
+        end_time = start_time + segment_duration
+        segment = audio[start_time:end_time]
+    output_stream = io.BytesIO()
+    segment.export(output_stream, format="wav")
+
+    # Now you can directly use the output_stream for feature extraction
+    output_stream.seek(0)  # Reset the stream position to the beginning
+
+    # Process and extract features from the segment
+    features = feature_extraction.all_feature_extraction(output_stream)
+
+    return features
+# output_file = "D:/miniproject/output_segment.wav"
+
+# Save the segment to a new file
+# segment.export(output_file, format="wav")

feature_extraction.py

@@ -0,0 +1,110 @@
+import librosa
+import numpy as np
+import joblib
+import soundfile as sf
+scaler = joblib.load("./models/std_scaler(1).pkl")
+
+
+def load_audio_from_uploaded_file(uploaded_file):
+    # Use the soundfile library to read the audio data and sample rate
+    audio_data, sample_rate = sf.read(uploaded_file)
+
+    return audio_data, sample_rate
+
+
+# sample_audio,sr = librosa.load(r"classical.00000.wav",sr = 44100)
+Fields = ['name', 'length', 'chroma_stft_mean', 'chroma_stft_var', 'rms_mean', 'rms_var',
+          'spectral_centroid_mean', 'spectral_centroid_var', 'spectral_bandwidth_mean', 'spectral_bandwidth_var',
+          'rolloff_mean', 'rolloff_var', 'zero_crossing_rate_mean', 'zero_crossing_rate_var',
+          'harmony_mean', 'harmony_var', 'percussive_mean', 'percussive_var', 'tempo',
+          'mfcc1_mean', 'mfcc1_var', 'mfcc2_mean', 'mfcc2_var', 'mfcc3_mean', 'mfcc3_var', 'mfcc4_mean', 'mfcc4_var',
+          'mfcc5_mean', 'mfcc5_var', 'mfcc6_mean', 'mfcc6_var', 'mfcc7_mean', 'mfcc7_var', 'mfcc8_mean', 'mfcc8_var',
+          'mfcc9_mean', 'mfcc9_var', 'mfcc10_mean', 'mfcc10_var', 'mfcc11_mean', 'mfcc11_var', 'mfcc12_mean',
+          'mfcc12_var',
+          'mfcc13_mean', 'mfcc13_var', 'mfcc14_mean', 'mfcc14_var', 'mfcc15_mean', 'mfcc15_var', 'mfcc16_mean',
+          'mfcc16_var',
+          'mfcc17_mean', 'mfcc17_var', 'mfcc18_mean', 'mfcc18_var', 'mfcc19_mean', 'mfcc19_var', 'mfcc20_mean',
+          'mfcc20_var']
+
+short_field = Fields[2:]
+
+
+def all_feature_extraction(audio_path, sample_rate=22050):
+    data_list = []
+    audio_df, sr = librosa.load(audio_path, sr=22050)
+    data_list.append(audio_path)
+    data_list.append(len(audio_df))
+    # 1. Chroma STFT
+    chroma_stft = librosa.feature.chroma_stft(y=audio_df, hop_length=512)
+    chroma_stft_mean = np.mean(chroma_stft)
+    chroma_stft_var = np.var(chroma_stft)
+    data_list.append(chroma_stft_mean)
+    data_list.append(chroma_stft_var)
+
+    # 2. RMS
+    rms = librosa.feature.rms(y=audio_df)
+    rms_mean = np.mean(rms)
+    rms_var = np.var(rms)
+    data_list.append(rms_mean)
+    data_list.append(rms_var)
+
+    spectral_centroid = librosa.feature.spectral_centroid(y=audio_df)
+    spectral_centroid_mean = np.mean(spectral_centroid)
+    spectral_centroid_var = np.var(spectral_centroid)
+    data_list.append(spectral_centroid_mean)
+    data_list.append(spectral_centroid_var)
+
+    spectral_bandwidth = librosa.feature.spectral_bandwidth(y=audio_df)
+    spectral_bandwidth_mean = np.mean(spectral_bandwidth)
+    spectral_bandwidth_var = np.var(spectral_bandwidth)
+    data_list.append(spectral_bandwidth_mean)
+    data_list.append(spectral_bandwidth_var)
+
+    spectral_rolloff = librosa.feature.spectral_rolloff(y=audio_df)
+    spectral_rolloff_mean = np.mean(spectral_rolloff)
+    spectral_rolloff_var = np.var(spectral_rolloff)
+    data_list.append(spectral_rolloff_mean)
+    data_list.append(spectral_rolloff_var)
+
+    zcr = librosa.feature.zero_crossing_rate(y=audio_df)
+    zcr_mean = np.mean(zcr)
+    zcr_var = np.var(zcr)
+    data_list.append(zcr_mean)
+    data_list.append(zcr_var)
+
+    harmonic, percussive = librosa.effects.hpss(y=audio_df)
+    harmonic_mean = np.mean(harmonic)
+    harmonic_var = np.var(harmonic)
+    percussive_mean = np.mean(percussive)
+    percussive_var = np.var(percussive)
+    data_list.append(harmonic_mean)
+    data_list.append(harmonic_var)
+    data_list.append(percussive_mean)
+    data_list.append(percussive_var)
+
+    tempo = librosa.feature.tempo(y=audio_df)
+    tempo = np.mean(tempo)
+    data_list.append(tempo)
+    mfccs = librosa.feature.mfcc(y=audio_df, sr=sr)
+    row_means = np.mean(mfccs, axis=1)
+    row_vars = np.var(mfccs, axis=1)
+    mfcc_means = {}
+    mfcc_vars = {}
+    for i in range(1, 21):
+        variable_name = f'mfcc{i}'
+        mfcc_means[variable_name] = row_means[i - 1]  # You can initialize with values if needed
+        mfcc_vars[variable_name] = row_vars[i - 1]
+    # Convert the dictionary values to a list
+    mfcc_list = [value for value in zip(mfcc_means.values(), mfcc_vars.values())]
+
+    for mean, var in mfcc_list:
+        data_list.append(mean)
+        data_list.append(var)
+    return data_list
+
+def scale(initial_features):
+    final_features = initial_features[2:]
+    final_features = np.array(final_features)
+    # Apply the loaded scaler to your single data point
+    scaled_data_point = scaler.transform([final_features])
+    return scaled_data_point

models/bn.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f123d228b0fc0654571fbfd957e23526cb380a9e909cf00fb2100dd52c573ead
+size 2555061

models/cnn.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d38f07cf80f7ed39a07f1d1652e38e3263519eb9bea309101502b45819e08a
+size 182963

models/crnn.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ee711027be2cae7385a07146efcecc056493f730a120dfe450ff4b6bdee2d2
+size 342493

models/knn.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ba96d036e23d7f20893202259a909569fae16c5004e3522c041f1e47a8eb8e
+size 3245884

models/logistic.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9071b17bf3b8d130b8842b7db22fafe9d2f7895ada07e4ba587c4ba877f276bb
+size 5783

models/model_bn.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121c293728854ab08cb35a7b8086cdaa12ab7f54fbafc3a35fa26950705d84a8
+size 2589340

models/model_cnn.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d805c96c78b1c7c0394596860358a0024c3bbffda602e0e8eda33f0137f936
+size 183464

models/model_crnn.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f09ea12931f67460b36814879aaab95d8946ff1b4a2f92190af33c97f029ac8
+size 347624

models/model_crnn1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55278fc28a3359c295b1a1d4000dfb1c8c61caaf2cfaa622fea938b702d99022
+size 351720

models/model_nn.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b05ae23e3fd3ccc5393667aafec862a4dae1f382bb998cacb65446099ee9cf3
+size 2515076

models/nn.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bb18ab39efcbdf61b20fb32107fa7a2e380f4a999ef0c2f5a25bc178b5448d
+size 2726129

models/nn1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ea85608e89d3b6f9dde8330c92ba7d225e51f5591d50e3bd90231b0d05771c
+size 2496636

models/scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759ba8b2d1b3c34529392efc7d0729b24f98d4f7677197b516c140ac79802f2c
+size 3311

models/std_scaler(1).pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12102947c64acba9e9b8c6c8b89f455282cbc22a23565bfe2e5c4c224fa4350
+size 3311

models/svm.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f280eacc31d08f200f5e2d85720a06d010223a8f098faf0641ee39948f13f49
+size 3059947

models/xgb.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa82bd2754da1bd9775f424ef6007dc6bffcf335492e6869edc58646f1bb52e
+size 18275161

models/xgb_mlb.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db529971c3f3e1d319502be2ec9015c3dc21a45b55bc800e26238295a3d502be
+size 4584698