Removed extra bits, added some print statements

app.py

@@ -7,7 +7,6 @@ from transformers import (
     AutoModelForSpeechSeq2Seq,
     AutoProcessor,
     pipeline,
-    WhisperProcessor,
 )
 
 
@@ -17,17 +16,12 @@ torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
 model_id = "openai/whisper-large-v3"
 
-# model = AutoModelForSpeechSeq2Seq.from_pretrained(
-#     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
-# )
 
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, low_cpu_mem_usage=True, use_safetensors=True
 )
 model.to(device)
 
-# processor = WhisperProcessor.from_pretrained("openai/whisper-base.en")
-
 processor = AutoProcessor.from_pretrained(model_id)
 
 pipe = pipeline(
@@ -46,14 +40,18 @@ pipe = pipeline(
 
 def transcribe_audio(audio):
     result = pipe(audio)
-    logging.info(f'TRANSCRIPTION {result["text"]}')
+    print(f'TRANSCRIPTION {result["text"]}')
+    try:
+        for r in result:
+            print(r)
+    except:
+        print("ERROR")
     return result
 
 
 input_audio = gr.Audio(
     sources=["microphone"],
     type="filepath",
-    # optional=True,
     waveform_options=gr.WaveformOptions(
         waveform_color="#01C6FF",
         waveform_progress_color="#0066B4",