try

app.py

@@ -0,0 +1,23 @@
+import gradio as gr
+from transformers import pipeline
+
+def transcribe_speech(filepath):
+    model_id = "chaouch/whisper-small-dv"  # update with your model id
+    pipe = pipeline("automatic-speech-recognition", model=model_id)
+    output = pipe(
+        filepath,
+        max_new_tokens=256,
+        generate_kwargs={
+            "task": "transcribe",
+            "language": "sinhalese",
+        },  # update with the language you've fine-tuned on
+        chunk_length_s=30,
+        batch_size=8,
+    )
+    return output["text"]
+
+if __name__ == "__main__":
+    demo = gr.Interface(fn=transcribe_speech,
+                        inputs=gr.Audio(sources="microphone", type="file"),
+                        outputs=gr.Textbox())
+    demo.launch(debug=True)