Spaces:
Runtime error
Runtime error
Commit
•
9dc988e
0
Parent(s):
Duplicate from samusander/Snore.Ai
Browse filesCo-authored-by: Samuel Sander <samusander@users.noreply.huggingface.co>
- .gitattributes +34 -0
- README.md +13 -0
- app.py +58 -0
- finalized_model.sav +0 -0
- requirements.txt +10 -0
.gitattributes
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Snore.Ai
|
3 |
+
emoji: 🌍
|
4 |
+
colorFrom: yellow
|
5 |
+
colorTo: pink
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 3.19.1
|
8 |
+
app_file: app.py
|
9 |
+
pinned: false
|
10 |
+
duplicated_from: samusander/Snore.Ai
|
11 |
+
---
|
12 |
+
|
13 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Imports
|
2 |
+
import gradio as gr
|
3 |
+
import tensorflow_io as tfio
|
4 |
+
from speechbrain.pretrained import EncoderClassifier
|
5 |
+
import torchaudio
|
6 |
+
from sklearn.linear_model import LogisticRegression
|
7 |
+
import joblib
|
8 |
+
import tensorflow as tf
|
9 |
+
import numpy as np
|
10 |
+
|
11 |
+
|
12 |
+
|
13 |
+
# Utility function for loading audio files and making sure the sample rate is correct.
|
14 |
+
@tf.function
|
15 |
+
def load_wav_16k_mono(filename):
|
16 |
+
"""Load a WAV file, convert it to a float tensor, resample to 16 kHz single-channel audio."""
|
17 |
+
file_contents = tf.io.read_file(filename)
|
18 |
+
wav, sample_rate = tf.audio.decode_wav(file_contents, desired_channels=1)
|
19 |
+
wav = tf.squeeze(wav, axis=-1)
|
20 |
+
sample_rate = tf.cast(sample_rate, dtype=tf.int64)
|
21 |
+
wav = tfio.audio.resample(wav, rate_in=sample_rate, rate_out=16000)
|
22 |
+
return wav
|
23 |
+
|
24 |
+
def extract_audio_embeddings(model, wav_audio_file_path: str) -> tuple:
|
25 |
+
"""Feature extractor that embeds audio into a vector."""
|
26 |
+
signal, fs = torchaudio.load(wav_audio_file_path) # Reformat audio signal into a tensor
|
27 |
+
embeddings = model.encode_batch(
|
28 |
+
signal
|
29 |
+
) # Pass tensor through pretrained neural net and extract representation
|
30 |
+
return embeddings
|
31 |
+
|
32 |
+
|
33 |
+
def detect_snoring(audio):
|
34 |
+
feature_extractor = EncoderClassifier.from_hparams(
|
35 |
+
"speechbrain/spkrec-xvect-voxceleb",
|
36 |
+
# run_opts={"device":"cuda"} # Uncomment this to run on GPU if you have one (optional)
|
37 |
+
)
|
38 |
+
filename = 'finalized_model.sav'
|
39 |
+
model = joblib.load(filename)
|
40 |
+
|
41 |
+
embeddings = extract_audio_embeddings(feature_extractor, audio)
|
42 |
+
embeddings_array = embeddings.cpu().numpy()[0]
|
43 |
+
output = model.predict_proba(embeddings_array)
|
44 |
+
output = np.round(output[:, 1])
|
45 |
+
if 1 in output:
|
46 |
+
output = "Snoring detected"
|
47 |
+
else:
|
48 |
+
output = "Snoring is not detected"
|
49 |
+
return output
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
# Defining the audio filepaths
|
54 |
+
audio = gr.inputs.Audio(type="filepath")
|
55 |
+
|
56 |
+
# Loading the gradio framwork
|
57 |
+
iface = gr.Interface(fn=detect_snoring,inputs=audio, outputs="text", title="Snore.AI", description="Detect Snotring with artificial intelligence.")
|
58 |
+
iface.launch()
|
finalized_model.sav
ADDED
Binary file (4.96 kB). View file
|
|
requirements.txt
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
scikit-learn
|
2 |
+
joblib
|
3 |
+
pandas
|
4 |
+
numpy
|
5 |
+
tensorflow
|
6 |
+
torch
|
7 |
+
tensorflow_io
|
8 |
+
pathlib
|
9 |
+
speechbrain
|
10 |
+
torchaudio
|