Update app.py

app.py

@@ -35,7 +35,7 @@ import torch
 #import torchaudio
 #import torchaudio.transforms as transforms
 
-from transformers import pipeline, AutoModel
+from transformers import pipeline #AutoModel
 
 import spacy
 import networkx as nx
@@ -68,14 +68,19 @@ pipe = pipeline("automatic-speech-recognition", model="NbAiLab/nb-whisper-large"
 
 @spaces.GPU()
 def transcribe_audio(audio_file, batch_size=16):
-    # Load the audio file into a numpy array
+    
+    # --check if audio_file is tuple
+    if isinstance(audio_file, tuple):
+        audio_file = audio_file[0]
+        
+    # --place audio file in numpy array
     audio = AudioSegment.from_wav(audio_file)
     samples = np.array(audio.get_array_of_samples())
     sample_rate = audio.frame_rate
 
     start_time = time.time()
 
-    # Transcribe the audio file
+    # --transcribe 
     outputs = pipe(samples, sampling_rate=sample_rate, batch_size=batch_size, return_timestamps=False)
     text = outputs["text"]
 
@@ -84,16 +89,16 @@ def transcribe_audio(audio_file, batch_size=16):
     output_time = end_time - start_time
     word_count = len(text.split())
 
-    # GPU usage
+    # --GPU usage
     memory = psutil.virtual_memory()
     gpu_utilization, gpu_memory = GPUInfo.gpu_usage()
     gpu_utilization = gpu_utilization[0] if len(gpu_utilization) > 0 else 0
     gpu_memory = gpu_memory[0] if len(gpu_memory) > 0 else 0
 
-    # CPU usage
+    # --CPU usage
     cpu_usage = psutil.cpu_percent(interval=1)
 
-    # System info string
+    # --system info string
     system_info = f"""
     *Memory: {memory.total / (1024 * 1024 * 1024):.2f}GB, used: {memory.percent}%, available: {memory.available / (1024 * 1024 * 1024):.2f}GB.*
     *Processing time: {output_time:.2f} seconds.*
@@ -108,8 +113,7 @@ def transcribe_audio(audio_file, batch_size=16):
 #              ------------summary section------------
 
 
-
-#          -----------------BLOCKS NEED EDIT....!--------------
+#          ------------for app integration later------------
 
 @spaces.GPU()
 def clean_text(text):