Update app.py

app.py

@@ -1,23 +1,21 @@
-import numpy as np
+from transformers import pipeline
 import gradio as gr
 
-notes = ["C", "C#", "D", "D#", "E", "F", "F#", "G", "G#", "A", "A#", "B"]
+model = pipeline("automatic-speech-recognition")
 
-def generate_tone(note, octave, duration):
-    sr = 48000
-    a4_freq, tones_from_a4 = 440, 12 * (octave - 4) + (note - 9)
-    frequency = a4_freq * 2 ** (tones_from_a4 / 12)
-    duration = int(duration)
-    audio = np.linspace(0, duration, duration * sr)
-    audio = (20000 * np.sin(audio * (2 * np.pi * frequency))).astype(np.int16)
-    return (sr, audio)
+def transcribe_audio(mic=None, file=None):
+  if mic is not None:
+    audio = mic
+  elif file is not None:
+    audio = file
+  else:
+    return("You must either provide a mic recording or a file")
+  transcription = model(audio)["text"]
+  return transcription
 
 gr.Interface(
-    generate_tone,
-    [
-        gr.inputs.Dropdown(notes, type="index"),
-        gr.inputs.Slider(4, 6, step=1),
-        gr.inputs.Textbox(type="number", default=1, label="Duration in seconds"),
-    ],
-    "audio",
+  fn=transcribe_audio,
+  inputs=[gr.inputs.Audio(source="microphone", type="filepath", optional=True),
+          gr.inputs.Audio(source ="upload", type="filepath", optional=True)],
+  outputs="text",
 ).launch()