Update app.py

app.py

@@ -9,20 +9,20 @@ description = """
 A demo of conformer-based speaker recognition. Paper: https://arxiv.org/abs/2104.02125
 """
 
-repo_id = "tflite-hub/conformer-lang-id"
+repo_id = "tflite-hub/conformer-speaker-encoder"
 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)
+hf_hub_download(repo_id=repo_id, filename="vad_long_model.tflite", local_dir=model_path)
+hf_hub_download(repo_id=repo_id, filename="vad_long_mean_stddev.csv", local_dir=model_path)
+hf_hub_download(repo_id=repo_id, filename="conformer_tisid_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"))
+runner = wav_to_dvector.WavToDvectorRunner(
+    vad_model_file=os.path.join(model_path, "vad_long_model.tflite"),
+    vad_mean_stddev_file=os.path.join(model_path, "vad_long_mean_stddev.csv"),
+    tisid_model_file=os.path.join(model_path, "conformer_tisid_medium.tflite"))
 
 def predict(enroll_audio, test_audio):
-    top_lang, _ = runner.wav_to_lang(enroll_audio)
-    return "Predicted language:" + top_lang
+    score = runner.compute_score([enroll_audio], test_audio)
+    return "Speaker similarity score: " + score
 
 if __name__ == "__main__":
     demo = gr.Interface(