Update app.py

app.py

@@ -8,6 +8,8 @@ import torch
 from transformers import AutoModelForCausalLM
 from transformers import AutoTokenizer
 # from next_word_prediction import GPT2
+import time
+
 
 ### code snippet
 gpt2 = AutoModelForCausalLM.from_pretrained("gpt2", return_dict_in_generate=True)
@@ -20,6 +22,8 @@ from share_btn import community_icon_html, loading_icon_html, share_js
 # get gpt2 model
 generator = pipeline('text-generation', model='gpt2')
 
+# get ASR
+p = pipeline("automatic-speech-recognition")
 
 # whisper model specification 
 model = whisper.load_model("tiny")
@@ -81,6 +85,23 @@ def inference(audio):
     return getText, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)
 
 
+def transcribe(audio, state=""):
+    time.sleep(1)
+    text = p(audio)["text"]
+    state += text + " "
+    return state, state
+
+gr.Interface(
+    fn=transcribe, 
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath"), 
+        "state"
+    ],
+    outputs=[
+        "textbox",
+        "state"
+    ],
+    live=True).launch()
 
 
 css = """