Create app.py

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+
+def transcribe(audio1, audio2):
+	sr1, y1 = audio1
+	sr2, y2 = audio2
+
+	def convertToMono(y):
+		if y.ndim > 1:
+			y = y.mean(axis=1)
+		
+		y = y.astype(np.float32)
+		y /= np.max(np.abs(y))
+		return y
+	# Convert to mono if stereo
+	y1 = convertToMono(y1)
+	y2 = convertToMono(y2)	
+
+	text1 = transcriber({"sampling_rate": sr1, "raw": y1})["text"]
+	text2 = transcriber({"sampling_rate": sr1, "raw": y2})["text"]
+	return text1 + " -- " + text2
+
+demo = gr.Interface(
+	transcribe,
+	[gr.Audio(sources="upload"), gr.Audio(sources="upload")],
+	["text"],
+)
+
+demo.launch()