Create app.py

app.py

@@ -0,0 +1,20 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.es")
+
+def transcribe(audio):
+    sr, y = audio
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+
+demo = gr.Interface(
+    transcribe,
+    gr.Audio(sources=["microphone"], type="numpy", label="xerra aqui..."),
+    "text",
+)
+
+demo.launch(debug=True)