update

app.py

@@ -4,14 +4,14 @@ import matplotlib.pyplot as plt
 import sounddevice as sd
 import numpy as np
 import pandas as pd
-# import torch
-# import torchaudio
+import torch
+import torchaudio
 import wave
 import io
 from scipy.io import wavfile
 # MODEL LOADING and INITIALISATION
-# model = torch.jit.load("snorenetv1_small.ptl")
-# model.eval()
+model = torch.jit.load("snorenetv1_small.ptl")
+model.eval()
 
 # Session state
 if 'text' not in st.session_state:
@@ -53,7 +53,6 @@ with st.expander('About this App'):
 
 wav_audio_data = st_audiorec()
 if wav_audio_data is not None:
-    
     data = np.frombuffer(wav_audio_data, dtype=np.int16)
     st.write(len(data))
     duration = len(data)//110000
@@ -65,7 +64,7 @@ if wav_audio_data is not None:
     scaled_data = np_array.astype(np.int16).tobytes()
     with io.BytesIO() as fp, wave.open(fp, mode="wb") as waveobj:
         waveobj.setnchannels(1)
-        waveobj.setframerate(sample_rate)
+        waveobj.setframerate(96000)
         waveobj.setsampwidth(2)
         waveobj.setcomptype("NONE", "NONE")
         waveobj.writeframes(scaled_data)
@@ -73,8 +72,16 @@ if wav_audio_data is not None:
     
     with open("output.wav", 'wb') as wav_file:
         wav_file.write(wav_make)
-    st.audio("output.wav" , format="audio/wav")
-    # st.audio(loaded_waveform, "audio/wav")
+    sr, waveform = wavfile.read('output.wav')
+    input_tensor = torch.tensor(waveform[:16000]).unsqueeze(0).to(torch.float32)
+    st.write(input_tensor.shape)
+    result = model(input_tensor)
+    if np.abs(result[0][0]) > np.abs(result[0][1]):
+        st.write("NON_SNORING")
+    else:
+        st.write("SNORING")
+
+    
     # PERCENTAGE OF SNORING PLOT