Update app.py

app.py

@@ -1,7 +1,34 @@
 import gradio as gr
+import os
+from sidlingvo import wav_to_lang
+from huggingface_hub import hf_hub_download
 
-def greet(name):
-    return "Hello " + name + "!!"
+title = "Spoken Language Identification"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+description = """
+A demo of conformer-based spoken language identification. Paper: https://arxiv.org/abs/2202.12163
+"""
+
+repo_id = "tflite-hub/conformer-lang-id"
+model_path = "models"
+hf_hub_download(repo_id=repo_id, filename="vad_short_model.tflite", local_dir=model_path)
+hf_hub_download(repo_id=repo_id, filename="vad_short_mean_stddev.csv", local_dir=model_path)
+hf_hub_download(repo_id=repo_id, filename="conformer_langid_medium.tflite", local_dir=model_path)
+
+runner = wav_to_lang.WavToLangRunner(
+    vad_model_file=os.path.join(model_path, "vad_short_model.tflite"),
+    vad_mean_stddev_file=os.path.join(model_path, "vad_short_mean_stddev.csv"),
+    langid_model_file=os.path.join(model_path, "conformer_langid_medium.tflite"))
+
+def predict(wav_file):
+    top_lang, _ = runner.wav_to_lang(wav_file)
+    return "Predicted language:" + top_lang
+
+if __name__ == "__main__":
+    demo = gr.Interface(
+        fn=predict,
+        inputs=gr.Audio(type="filepath"),
+        outputs="text",
+        title=title,
+        description=description,)
+    demo.launch()