Update app.py

app.py

@@ -6,6 +6,7 @@ from fastai.vision.all import load_learner
 import time
 import base64
 from deepface import DeepFace
+import torchaudio, torch
 
 # import pathlib
 # temp = pathlib.PosixPath
@@ -42,6 +43,20 @@ def video_processing(video_file, encoded_video):
         video_file = "temp_video.mp4"
 
     start_time = time.time()
+
+    subprocess.call(["ffmpeg", "-i", 'source_videos/A message from longbeachgriffy.mp4', "audio.wav"])
+    waveform, sample_rate = torchaudio.load("audio.wav")
+    waveform, sample_rate
+
+    waveform, sample_rate = torchaudio.load("audio.wav")
+    resampler = torchaudio.transforms.Resample(sample_rate, 16000)
+    waveform = resampler(waveform)[0]
+
+    input_features = processor(waveform.squeeze(dim=0), return_tensors="pt").input_features 
+    predicted_ids = model.generate(input_features)
+    
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+    print(transcription[0])
     
     video_capture = cv2.VideoCapture(video_file)
     on_camera = 0