update

examples/wenet/toolbox_infer.py

@@ -57,17 +57,24 @@ def main():
     nn_model_file = local_model_dir / m_dict["nn_model_file"]
     tokens_file = local_model_dir / m_dict["tokens_file"]
 
-    recognizer = models.load_recognizer(
-        repo_id=m_dict["repo_id"],
-        nn_model_file=nn_model_file.as_posix(),
-        tokens_file=tokens_file.as_posix(),
-        sub_folder=m_dict["sub_folder"],
-        local_model_dir=local_model_dir,
-        recognizer_type=m_dict["recognizer_type"],
+    recognizer = models.load_sherpa_offline_recognizer(
+        nn_model_file=nn_model_file,
+        tokens_file=tokens_file,
         decoding_method="greedy_search",
         num_active_paths=2,
     )
 
+    # recognizer = models.load_recognizer(
+    #     repo_id=m_dict["repo_id"],
+    #     nn_model_file=nn_model_file.as_posix(),
+    #     tokens_file=tokens_file.as_posix(),
+    #     sub_folder=m_dict["sub_folder"],
+    #     local_model_dir=local_model_dir,
+    #     recognizer_type=m_dict["recognizer_type"],
+    #     decoding_method="greedy_search",
+    #     num_active_paths=2,
+    # )
+
     # feat_config = sherpa.FeatureConfig(normalize_samples=False)
     # feat_config.fbank_opts.frame_opts.samp_freq = args.sample_rate
     # feat_config.fbank_opts.mel_opts.num_bins = 80

toolbox/k2_sherpa/models.py

@@ -102,11 +102,6 @@ def load_recognizer(repo_id: str,
         )
 
     if recognizer_type == EnumRecognizerType.sherpa_offline_recognizer.value:
-        print("nn_model_file: {}".format(nn_model_file))
-        print("tokens_file: {}".format(tokens_file))
-        print("decoding_method: {}".format(decoding_method))
-        print("num_active_paths: {}".format(num_active_paths))
-
         recognizer = load_sherpa_offline_recognizer(
             nn_model_file=nn_model_file,
             tokens_file=tokens_file,