Update app.py

app.py

@@ -55,7 +55,7 @@ SIDEBAR_INFO = f"""
 </div>
 """
 
-#              ------------transcribe section------------
+# ------------transcribe section------------
 
 @spaces.GPU()
 def convert_to_wav(filepath):
@@ -64,13 +64,20 @@ def convert_to_wav(filepath):
     os.system(f'ffmpeg -i "{filepath}" -ar 16000 -ac 1 -c:a pcm_s16le "{audio_file}"')
     return audio_file
 
-pipe = pipeline("automatic-speech-recognition", model="NbAiLab/nb-whisper-large", chunk_length_s=30)
+pipe = pipeline("automatic-speech-recognition", model="NbAiLab/nb-whisper-large", chunk_length_s=30, generate_kwargs={'task': 'transcribe', 'language': 'no'})
 
 @spaces.GPU()
 def transcribe_audio(audio_file, batch_size=16):
+    # Load the audio file into a 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()
 
-    outputs = pipe(audio_file, batch_size=batch_size, return_timestamps=False)
+    # Transcribe the audio file
+    outputs = pipe(samples, sampling_rate=sample_rate, batch_size=batch_size, return_timestamps=False)
+    text = outputs["text"]
 
     end_time = time.time()
     
@@ -97,6 +104,7 @@ def transcribe_audio(audio_file, batch_size=16):
 
     return text.strip(), system_info
 
+
 #              ------------summary section------------