Update app.py

app.py

@@ -22,15 +22,20 @@ import gradio as gr
 
 model = EncoderASR.from_hparams("speechbrain/asr-wav2vec2-dvoice-wolof")
 
-def transcribe(audio_or_file):
-    if isinstance(audio_or_file, str):  # If input is a file path
-        return model.transcribe_file(audio_or_file)
-    else:  # If input is audio from microphone
-        return model.transcribe_array(audio_or_file)
+def transcribe(stream, new_chunk):
+    sr, y = new_chunk
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+
+    if stream is not None:
+        stream = np.concatenate([stream, y])
+    else:
+        stream = y
+    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]
 
 demo = gr.Interface(
     transcribe,
-    ["state", gr.inputs.Microphone(source="local", type="wav"), "text"],
+    ["state", gr.Audio(sources=["microphone"], streaming=True)],
     ["state", "text"],
     live=True,
 )