test main

app.py

@@ -1,6 +1,9 @@
 import streamlit as st
 from st_audiorec import st_audiorec
 
+import librosa
+import soundfile
+
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from datasets import load_dataset
 import torch
@@ -12,9 +15,10 @@ audio_transcription: str = None
 def main ():
     
     init_model()
+    print('Init model successful')
     # x = st.slider('Select a value')
     # st.write(x, 'squared is', x * x)
-
+"""
     wav_audio_data = st_audiorec()
 
     if wav_audio_data is not None:
@@ -23,7 +27,7 @@ def main ():
     dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
     sample = dataset[0]["audio"]
     st.write('Sample:', sample)
-
+"""
 async def init_model ():
     device = "cuda:0" if torch.cuda.is_available() else "cpu"
     torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32