From 4ace5a95b052d338947fc88809a440ccd55cf6b4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 十一月 2023 16:39:52 +0800
Subject: [PATCH] funasr pages

---
 funasr/datasets/large_datasets/utils/tokenize.py |   40 +++++++++++++++++++++++++++++++---------
 1 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index d8ceff2..34a97c1 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 import re
 import numpy as np
+from funasr.datasets.large_datasets.utils.hotword_utils import sample_hotword
 
 def forward_segment(text, seg_dict):
     word_list = []
@@ -17,38 +18,59 @@
     return word_list
 
 def seg_tokenize(txt, seg_dict):
+    pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
     out_txt = ""
     for word in txt:
+        word = word.lower()
         if word in seg_dict:
             out_txt += seg_dict[word] + " "
         else:
-            out_txt += "<unk>" + " "
+            if pattern.match(word):
+                for char in word:
+                    if char in seg_dict:
+                        out_txt += seg_dict[char] + " "
+                    else:
+                        out_txt += "<unk>" + " "
+            else:
+                out_txt += "<unk>" + " "
     return out_txt.strip().split()
 
 def tokenize(data,
              vocab=None,
              seg_dict=None,
              punc_dict=None,
-             bpe_tokenizer=None):
+             bpe_tokenizer=None,
+             hw_config=None):
     assert "text" in data
     assert isinstance(vocab, dict)
     text = data["text"]
     token = []
     vad = -2
-
     if bpe_tokenizer is not None:
-        text = bpe_tokenizer.text2tokens("".join(text))
-
+        text = bpe_tokenizer.text2tokens(" ".join(text))
     if seg_dict is not None:
         assert isinstance(seg_dict, dict)
-        txt = forward_segment("".join(text).lower(), seg_dict)
-        text = seg_tokenize(txt, seg_dict)
+        text = seg_tokenize(text, seg_dict)
 
     length = len(text)
+    if 'hw_tag' in data:
+        pre_index = None
+        if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
+            # enable preset hotword detect in sampling
+            for hw in hw_config['pre_hwlist']:
+                hw = " ".join(seg_tokenize(hw, seg_dict))
+                _find = " ".join(text).find(hw)
+                if _find != -1:
+                    # _find = text[:_find].count(" ")  # bpe sometimes
+                    pre_index = [_find, _find + max(hw.count(" "), 1)]
+                    break
+        hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
+        data['hotword_indxs'] = hotword_indxs
+        del data['hw_tag']
     for i in range(length):
         x = text[i]
-        if i == length-1 and "punc" in data and text[i].startswith("vad:"):
-            vad = x[-1][4:]
+        if i == length-1 and "punc" in data and x.startswith("vad:"):
+            vad = x[4:]
             if len(vad) == 0:
                 vad = -1
             else:

--
Gitblit v1.9.1