test

app.py

@@ -5,18 +5,23 @@ import time
 pipe = pipeline("automatic-speech-recognition", model="Artanis1551/whisper_romanian3")
 
 
-def transcribe(audio, state=""):
-    text = pipe(audio)["text"]
+def transcribe(rec=None, state=""):
+    if rec is not None:
+        audio = rec
+        text = pipe(audio)["text"]
+        state += text + ". "
+    else:
+        text = ""
+    return text, state
 
-    print(text)
-    state += text + " "
-    return state, state
 
-
-gr.Interface(
-    title="Romanian Speech Transcription",
+iface = gr.Interface(
     fn=transcribe,
     inputs=[gr.Audio(source="microphone", type="filepath", streaming=True), "state"],
-    outputs=["textbox", "state"],
+    outputs=["text", "state"],
+    title="Romanian Transcription Test",
     live=True,
-).launch()
+)
+
+
+iface.launch()