Modified app and requirements.txt

app.py

@@ -1,16 +1,22 @@
 from transformers import pipeline
 import gradio as gr
 import time
+from faster_whisper import WhisperModel
 
-p = pipeline("automatic-speech-recognition")
+model_size = "large-v2
+
+model = WhisperModel(model_size, device="cpu", compute_type="int8")
 
 
 def transcribe(audio, state=""):
-    time.sleep(2)
-    text = p(audio)["text"]
-    state += text + " "
-    return state, state
+    segments, info = model.transcribe(audio, beam_size=5)
+
+    print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
+
+    for segment in segments:
+        print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
 
+        return segment.text
 
 gr.Interface(
     fn=transcribe,

requirements.txt

@@ -2,3 +2,4 @@ gradio==3.16.2
 transformers
 torch
 deepspeech==0.8.2
+faster-whisper