From d783b24ba7d8a03dabfa2139fcbf40c216e0ea3d Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 三月 2023 19:34:52 +0800
Subject: [PATCH] Merge pull request #199 from alibaba-damo-academy/dev_xw

---
 funasr/bin/asr_inference_uniasr.py |   27 ++++++++++++++-------------
 1 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/funasr/bin/asr_inference_uniasr.py b/funasr/bin/asr_inference_uniasr.py
index c50bf17..ac71538 100644
--- a/funasr/bin/asr_inference_uniasr.py
+++ b/funasr/bin/asr_inference_uniasr.py
@@ -46,7 +46,7 @@
 
     Examples:
         >>> import soundfile
-        >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+        >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
         >>> audio, rate = soundfile.read("speech.wav")
         >>> speech2text(audio)
         [(text, token, token_int, hypothesis object), ...]
@@ -398,6 +398,19 @@
     else:
         device = "cpu"
     
+    if param_dict is not None and "decoding_model" in param_dict:
+        if param_dict["decoding_model"] == "fast":
+            decoding_ind = 0
+            decoding_mode = "model1"
+        elif param_dict["decoding_model"] == "normal":
+            decoding_ind = 0
+            decoding_mode = "model2"
+        elif param_dict["decoding_model"] == "offline":
+            decoding_ind = 1
+            decoding_mode = "model2"
+        else:
+            raise NotImplementedError("unsupported decoding model {}".format(param_dict["decoding_model"]))
+
     # 1. Set random-seed
     set_all_random_seed(seed)
 
@@ -440,18 +453,6 @@
             if isinstance(raw_inputs, torch.Tensor):
                 raw_inputs = raw_inputs.numpy()
             data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
-        if param_dict is not None and "decoding_model" in param_dict:
-            if param_dict["decoding_model"] == "fast":
-                speech2text.decoding_ind = 0
-                speech2text.decoding_mode = "model1"
-            elif param_dict["decoding_model"] == "normal":
-                speech2text.decoding_ind = 0
-                speech2text.decoding_mode = "model2"
-            elif param_dict["decoding_model"] == "offline":
-                speech2text.decoding_ind = 1
-                speech2text.decoding_mode = "model2"
-            else:
-                raise NotImplementedError("unsupported decoding model {}".format(param_dict["decoding_model"]))
         loader = ASRTask.build_streaming_iterator(
             data_path_and_name_and_type,
             dtype=dtype,

--
Gitblit v1.9.1