Duplicate from samusander/Snore.Ai

Co-authored-by: Samuel Sander <samusander@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,13 @@
+---
+title: Snore.Ai
+emoji: 🌍
+colorFrom: yellow
+colorTo: pink
+sdk: gradio
+sdk_version: 3.19.1
+app_file: app.py
+pinned: false
+duplicated_from: samusander/Snore.Ai
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,58 @@
+# Imports
+import gradio as gr
+import tensorflow_io as tfio
+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 audio filepaths
+audio = gr.inputs.Audio(type="filepath")
+
+# Loading the gradio framwork
+iface = gr.Interface(fn=detect_snoring,inputs=audio, outputs="text", title="Snore.AI", description="Detect Snotring with artificial intelligence.")
+iface.launch()

requirements.txt

@@ -0,0 +1,10 @@
+scikit-learn
+joblib
+pandas
+numpy
+tensorflow
+torch
+tensorflow_io
+pathlib
+speechbrain
+torchaudio