modal loads

app.py

@@ -1,8 +1,29 @@
+
 import gradio as gr
 import numpy as np
 from faster_whisper import WhisperModel
+from faster_whisper.transcribe import Segment
+
+audio_model = WhisperModel("tiny.en", device="cpu", compute_type="int8")
+transcription = ['']
+
+def transcribe(SampleRate, data):
+    segments, info = audio_model.transcribe(data, beam_size=5)
+    result = (list(segments))
+    text = ""
+
+    if result and len(result) > 0:
+        text = result[0].text
+        print("Text:", text)
+    else:
+        text = ""
+        print("No text found")
+        print(result)
+    
+
+
+    return(text)
 
-model = WhisperModel("tiny.en")
 
 def normaliseData(audioInput, stream):
     sr, y = audioInput
@@ -18,9 +39,11 @@ def normaliseData(audioInput, stream):
         stream = np.concatenate([stream, y])
     else:
         stream = y
+
+    words = transcribe(sr, y)
     
     # Return the stream as state and a string representation of the array for display
-    return stream, str(stream)
+    return stream, words,
 
 
 with gr.Blocks() as demo:
@@ -35,11 +58,3 @@ with gr.Blocks() as demo:
     )
 demo.launch()
 
-
-
-
-
-segments, info = model.transcribe("audio.mp3")
-for segment in segments:
-    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
-