From e451eb799a5bccd53dfd4b86cf66a4668b0088b7 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期三, 06 三月 2024 15:31:47 +0800
Subject: [PATCH] infer for word punc model

---
 funasr/models/ct_transformer/model.py |   22 +++++++++++++++++++---
 1 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/funasr/models/ct_transformer/model.py b/funasr/models/ct_transformer/model.py
index 8c3f043..1891ac7 100644
--- a/funasr/models/ct_transformer/model.py
+++ b/funasr/models/ct_transformer/model.py
@@ -3,6 +3,7 @@
 # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
 #  MIT License  (https://opensource.org/licenses/MIT)
 
+import copy
 import torch
 import numpy as np
 import torch.nn.functional as F
@@ -333,19 +334,34 @@
                 elif new_mini_sentence[-1] == ",":
                     new_mini_sentence_out = new_mini_sentence[:-1] + "."
                     new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [self.sentence_end_id]
-                elif new_mini_sentence[-1] != "銆�" and new_mini_sentence[-1] != "锛�" and len(new_mini_sentence[-1].encode())==0:
+                elif new_mini_sentence[-1] != "銆�" and new_mini_sentence[-1] != "锛�" and len(new_mini_sentence[-1].encode())!=1:
                     new_mini_sentence_out = new_mini_sentence + "銆�"
                     new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [self.sentence_end_id]
+                    if len(punctuations): punctuations[-1] = 2
                 elif new_mini_sentence[-1] != "." and new_mini_sentence[-1] != "?" and len(new_mini_sentence[-1].encode())==1:
                     new_mini_sentence_out = new_mini_sentence + "."
                     new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [self.sentence_end_id]
-            # keep a punctuations array for punc segment
+                    if len(punctuations): punctuations[-1] = 2
+            # keep a punctuations array for punc segment 
             if punc_array is None:
                 punc_array = punctuations
             else:
                 punc_array = torch.cat([punc_array, punctuations], dim=0)
+        # post processing when using word level punc model
+        if jieba_usr_dict:
+            len_tokens = len(tokens)
+            new_punc_array = copy.copy(punc_array).tolist()
+            # for i, (token, punc_id) in enumerate(zip(tokens[::-1], punc_array.tolist()[::-1])):
+            for i, token in enumerate(tokens[::-1]):
+                if '\u0e00' <= token[0] <= '\u9fa5': # ignore en words
+                    if len(token) > 1:
+                        num_append = len(token) - 1
+                        ind_append = len_tokens - i - 1
+                        for _ in range(num_append):
+                            new_punc_array.insert(ind_append, 1)
+        punc_array = torch.tensor(new_punc_array)
+        
         result_i = {"key": key[0], "text": new_mini_sentence_out, "punc_array": punc_array}
         results.append(result_i)
-    
         return results, meta_data
 

--
Gitblit v1.9.1