Update app.py

app.py

@@ -22,8 +22,7 @@ from pyannote.audio import Pipeline
 from pyannote.core import Annotation, Segment, Timeline
 import datetime as dt
 
-enableDenoise = False
-earlyCleanup = True
+
 
 # [None,Low,Medium,High,Debug]
 # [0,1,2,3,4]
@@ -82,37 +81,14 @@ def save_data(
     scheduler.append(data)
 
 def processFile(filePath):
-    global attenLimDb
-    global gainWindow
-    global minimumGain
-    global maximumGain
     print("Loading file")
-    waveformList, sampleRate = su.splitIntoTimeSegments(filePath,600)
+    waveform, sampleRate = torchaudio.load(filePath)
     print("File loaded")
-    enhancedWaveformList = []
-    if (enableDenoise):
-        print("Denoising")
-    for w in waveformList:
-        if (enableDenoise):
-            newW = enhance(dfModel,dfState,w,atten_lim_db=attenLimDB).detach().cpu()
-            enhancedWaveformList.append(newW)
-        else:
-            enhancedWaveformList.append(w)
-    if (enableDenoise):
-        print("Audio denoised")
-    waveformEnhanced = su.combineWaveforms(enhancedWaveformList)    
-    if (earlyCleanup):
-        del enhancedWaveformList
-    print("Equalizing Audio")
-    waveform_gain_adjusted = su.equalizeVolume()(waveformEnhanced,sampleRate,gainWindow,minimumGain,maximumGain)
-    if (earlyCleanup):
-        del waveformEnhanced
-    print("Audio Equalized")
     print("Detecting speakers")
-    diarization_output = pipeline({"waveform": waveform_gain_adjusted, "sample_rate": sampleRate})
+    diarization_output = pipeline({"waveform": waveform, "sample_rate": sampleRate})
     annotations = diarization_output.speaker_diarization
     print("Speakers Detected")
-    totalTimeInSeconds = int(waveform_gain_adjusted.shape[-1]/sampleRate)
+    totalTimeInSeconds = int(waveform.shape[-1] / sampleRate)
     print("Time in seconds calculated")
     return annotations, totalTimeInSeconds
     
@@ -335,12 +311,6 @@ sample_data = [f"CHEM1402_gt/24F_CHEM1402_Night_Class_Week_{i}_gt.rttm" for i in
 
 scheduler = ps.ParquetScheduler(repo_id="Sonogram/SampleDataset")
 
-secondDifference = 5
-gainWindow = 4
-minimumGain = -45
-maximumGain = -5
-attenLimDB = 3
-
 isGPU = False
 
 try:
@@ -356,10 +326,6 @@ except RuntimeError as e:
     print(f"Using {device} instead.")
 #device = xm.xla_device()
 
-if (enableDenoise):
-    # Instantiate and prepare model for training.
-    dfModel, dfState, _ = init_df(model_base_dir="DeepFilterNet3")
-    dfModel.to(device)#torch.device("cuda"))
 pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization-3.1")
 pipeline.to(device)#torch.device("cuda"))