From 0cc7af2c894a31f1b6d95d8af7e4efa414e2a11b Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 07 四月 2023 15:54:21 +0800
Subject: [PATCH] Merge pull request #328 from alibaba-damo-academy/dev_cmz2

---
 funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py |   36 ++++++++++++++++++++++++++++++++++--
 1 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py b/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
index 2edde11..0df954e 100644
--- a/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
+++ b/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
@@ -188,7 +188,7 @@
                  input_content: List[Union[np.ndarray, np.ndarray]]) -> np.ndarray:
         input_dict = dict(zip(self.get_input_names(), input_content))
         try:
-            return self.session.run(None, input_dict)
+            return self.session.run(self.get_output_names(), input_dict)
         except Exception as e:
             raise ONNXRuntimeError('ONNXRuntime inferece failed.') from e
 
@@ -215,6 +215,38 @@
         if not model_path.is_file():
             raise FileExistsError(f'{model_path} is not a file.')
 
+def split_to_mini_sentence(words: list, word_limit: int = 20):
+    assert word_limit > 1
+    if len(words) <= word_limit:
+        return [words]
+    sentences = []
+    length = len(words)
+    sentence_len = length // word_limit
+    for i in range(sentence_len):
+        sentences.append(words[i * word_limit:(i + 1) * word_limit])
+    if length % word_limit > 0:
+        sentences.append(words[sentence_len * word_limit:])
+    return sentences
+
+def code_mix_split_words(text: str):
+    words = []
+    segs = text.split()
+    for seg in segs:
+        # There is no space in seg.
+        current_word = ""
+        for c in seg:
+            if len(c.encode()) == 1:
+                # This is an ASCII char.
+                current_word += c
+            else:
+                # This is a Chinese char.
+                if len(current_word) > 0:
+                    words.append(current_word)
+                    current_word = ""
+                words.append(c)
+        if len(current_word) > 0:
+            words.append(current_word)
+    return words
 
 def read_yaml(yaml_path: Union[str, Path]) -> Dict:
     if not Path(yaml_path).exists():
@@ -226,7 +258,7 @@
 
 
 @functools.lru_cache()
-def get_logger(name='rapdi_paraformer'):
+def get_logger(name='funasr_onnx'):
     """Initialize and get a logger by name.
     If the logger has not been initialized, this method will initialize the
     logger by adding one or two handlers, otherwise the initialized logger will

--
Gitblit v1.9.1