Update app.py

app.py

@@ -1,41 +1,17 @@
 import soundfile as sf
 import torch
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
-import argparse
-from glob import glob
-import subprocess
 import gradio as gr
 
 
-def get_filename(wav_file):
-    filename_local = wav_file.split('/')[-1][:-4]
-    filename_new = '/tmp/'+filename_local+'_16.wav'
-    
-    
-    subprocess.call(["sox {} -r {} -b 16 -c 1 {}".format(wav_file, str(16000), filename_new)], shell=True)
-    return filename_new
-
-
 
 def parse_transcription(wav_file):
-    # load pretrained model
-    
-    # load audio
-
-    
-    #wav_file = get_filename(wav_file.name)
     audio_input, sample_rate = sf.read(wav_file.name)
-    #test_file = resampler(test_file[0])
-
-    # pad input values and return pt tensor
     input_values = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt").input_values
 
-    # INFERENCE
-    # retrieve logits & take argmax
     logits = model(input_values).logits
     predicted_ids = torch.argmax(logits, dim=-1)
 
-    # transcribe
     transcription = processor.decode(predicted_ids[0], skip_special_tokens=True)
     return transcription