updt

app.py

@@ -1,42 +1,43 @@
 import os
 import numpy as np
 import gradio as gr
-#try:
-#    import tensorflow  # required in Colab to avoid protobuf compatibility issues
-#except ImportError:
-#    pass
-
-#import torch
-#import pandas as pd
 import whisper
-#import torchaudio
-
-#from tqdm.notebook import tqdm
-
 
-#DEVICE = "cuda" if torch.cuda.is_available() else "CPU"
 model = whisper.load_model("base.en")
 
-def fun(audio):
-  result = model.transcribe(audio)
-  return result["text"]
+def fun(audio, state=''):
+  text = model.transcribe(audio)["text"]
+  state += text + " "
+  return state, state
   
-# predict without timestamps for short-form transcription
-#options = whisper.DecodingOptions(language="en", without_timestamps=True)
-
-
-#for mels, texts in tqdm(loader):
-#    results = model.decode(mels, options)
-#    hypotheses.extend([result.text for result in results])
-#    references.extend(texts)
-
+def transcribe(audio, state=""):
+    text = p(audio)["text"]
+    state += text + " "
+    return state, state
+
+# Set the starting state to an empty string
+
+#gr.Interface(
+#    fn=transcribe, 
+#    inputs=[
+#        gr.Audio(source="microphone", type="filepath", streaming=True), 
+#        "state" 
+#    ],
+#    outputs=[
+#        "textbox",
+#        "state"
+#    ],
+#    live=True).launch()
+    
+    
 gr.Interface(
     title = 'Testing Whisper', 
     fn=fun, 
     inputs=[
-        gr.inputs.Audio(source="microphone", streaming = "True" ) #,type="filepath")
+        gr.inputs.Audio(source="microphone", streaming = True, type="filepath"),
+        "state"
     ],
     outputs=[
-        "textbox"
+        "textbox", "state"
     ],
     live=True).launch()