Update app.py

app.py

@@ -5,6 +5,11 @@ This script calls the model from openai api to predict the next few words in a c
 import os
 from pprint import pprint
 import sys
+'''
+This script calls the model from openai api to predict the next few words in a conversation.
+'''
+import os
+import sys
 import openai
 import gradio as gr
 os.system("pip install git+https://github.com/openai/whisper.git")
@@ -44,7 +49,7 @@ def transcribe(audio_file):
     transcription = asr_model.transcribe(audio_file)["text"]
     return transcription
 
-def debug_inference(audio, prompt, model, temperature, state=""):
+def inference(audio, prompt, model, temperature):
     # Transcribe with Whisper
     print("The audio is:", audio)
     transcript = transcribe(audio)
@@ -60,7 +65,7 @@ def debug_inference(audio, prompt, model, temperature, state=""):
 
     infers = []
     temp = []
-    infered=[]
+    #infered=[]
     for i in range(5):
         print("print1 ", response['choices'][i]['text'])
         temp.append(response['choices'][i]['text'])
@@ -72,17 +77,24 @@ def debug_inference(audio, prompt, model, temperature, state=""):
         infers = list(map(lambda x: x.replace("\n", ""), temp))
         #infered = list(map(lambda x: x.split(','), infers))
 
-    return transcript, state, infers, text
+    return transcript, infers
+
 
 # get audio from microphone 
-gr.Interface(
-    fn=debug_inference, 
-    inputs=[gr.inputs.Audio(source="microphone", type="filepath"),
-            gr.inputs.Textbox(lines=15, placeholder="Enter a prompt here"),
-            gr.inputs.Dropdown(["text-ada-001", "text-davinci-002", "text-davinci-003", "gpt-3.5-turbo"], label="Model"),
-            gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.8, step=0.1, label="Temperature"),
-            "state"
-            ],
-    outputs=["textbox","state","textbox", "textbox"],
-    # examples=[["example_in-the-mood-to-eat.m4a", EXAMPLE_PROMPT, "text-ada-001", 0.8, ""],["","","",0.9,""]],
-    live=False).launch()
+with gr.Blocks() as face:
+    with gr.Row():
+        with gr.Column():
+            audio = gr.Audio(source="microphone", type="filepath")
+            promptText = gr.inputs.Textbox(lines=15, placeholder="Enter a prompt here"),
+            dropChoice = gr.inputs.Dropdown(["text-ada-001", "text-davinci-002", "text-davinci-003", "gpt-3.5-turbo"], label="Model"),
+            sliderChoice = gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.8, step=0.1, label="Temperature")
+            transcribe_btn = gr.Button(value="Transcribe")
+        with gr.Column():
+            script = gr.Textbox(label="text...")
+            options = gr.Textbox(label="predictions...")
+
+    transcribe_btn.click(inference, inputs=[audio, promptText, dropChoice, sliderChoice] outputs=[script, options])
+    examples = gr.Examples(examples=["Sedan, Truck, SUV", "Dalmaion, Shepherd, Lab, Mutt"],
+                           inputs=[options])
+
+face.launch()