Update app.py

app.py

@@ -1,29 +1,58 @@
 # Imports
-from sklearn.linear_model import LogisticRegression
-from sklearn.model_selection import cross_val_predict
-from sklearn.metrics import accuracy_score
-import joblib
-import os
-import pandas as pd
-import numpy as np
-import random
-import tensorflow as tf
-import torch
-from tqdm import tqdm
+import gradio as gr
 import tensorflow_io as tfio
-from pathlib import Path
 from speechbrain.pretrained import EncoderClassifier
 import torchaudio
+from sklearn.linear_model import LogisticRegression
+import joblib
+import tensorflow as tf
+import numpy as np
+
+
+
+# Utility function for loading audio files and making sure the sample rate is correct.
+@tf.function
+def load_wav_16k_mono(filename):
+    """Load a WAV file, convert it to a float tensor, resample to 16 kHz single-channel audio."""
+    file_contents = tf.io.read_file(filename)
+    wav, sample_rate = tf.audio.decode_wav(file_contents, desired_channels=1)
+    wav = tf.squeeze(wav, axis=-1)
+    sample_rate = tf.cast(sample_rate, dtype=tf.int64)
+    wav = tfio.audio.resample(wav, rate_in=sample_rate, rate_out=16000)
+    return wav
+
+def extract_audio_embeddings(model, wav_audio_file_path: str) -> tuple:
+    """Feature extractor that embeds audio into a vector."""
+    signal, fs = torchaudio.load(wav_audio_file_path)  # Reformat audio signal into a tensor
+    embeddings = model.encode_batch(
+        signal
+    )  # Pass tensor through pretrained neural net and extract representation
+    return embeddings
+
+
+def detect_snoring(audio):
+  feature_extractor = EncoderClassifier.from_hparams(
+  "speechbrain/spkrec-xvect-voxceleb",
+  # run_opts={"device":"cuda"}  # Uncomment this to run on GPU if you have one (optional)
+  )
+  filename = 'finalized_model.sav'
+  model = joblib.load(filename)
 
+  embeddings = extract_audio_embeddings(feature_extractor, audio)
+  embeddings_array = embeddings.cpu().numpy()[0]
+  output = model.predict_proba(embeddings_array)
+  output = np.round(output[:, 1])
+  if 1 in output:
+    output = "Snoring detected"
+  else:
+    output = "Snoring is not detected"
+  return output
 
 
-# Defining the transcription function
-def snoring(audio):
-    return text
 
 # Defining the audio filepaths
 audio = gr.inputs.Audio(type="filepath")
 
 # Loading the gradio framwork
-iface = gr.Interface(fn=snoring,inputs=audio, outputs="text", title="Snore.AI", description="Detect Snotring with artificial intelligence.")
+iface = gr.Interface(fn=detect_snoring,inputs=audio, outputs="text", title="Snore.AI", description="Detect Snotring with artificial intelligence.")
 iface.launch()