From 9cc37eaa8af50db2ffad3fc02746547ef995a870 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期四, 28 九月 2023 15:47:43 +0800
Subject: [PATCH] add postprocess for en-bpe
---
funasr/runtime/onnxruntime/src/vocab.cpp | 20 ++++++++++++++++++--
1 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/funasr/runtime/onnxruntime/src/vocab.cpp b/funasr/runtime/onnxruntime/src/vocab.cpp
index c29156f..95174c7 100644
--- a/funasr/runtime/onnxruntime/src/vocab.cpp
+++ b/funasr/runtime/onnxruntime/src/vocab.cpp
@@ -75,20 +75,36 @@
return false;
}
-string Vocab::Vector2StringV2(vector<int> in)
+string Vocab::Vector2StringV2(vector<int> in, std::string language)
{
int i;
list<string> words;
int is_pre_english = false;
int pre_english_len = 0;
int is_combining = false;
- string combine = "";
+ std::string combine = "";
+ std::string unicodeChar = "鈻�";
for (auto it = in.begin(); it != in.end(); it++) {
string word = vocab[*it];
// step1 space character skips
if (word == "<s>" || word == "</s>" || word == "<unk>")
continue;
+ if (language == "en-bpe"){
+ size_t found = word.find(unicodeChar);
+ if(found != std::string::npos){
+ if (combine != ""){
+ if (words.size() != 0){
+ combine = " " + combine;
+ }
+ words.push_back(combine);
+ }
+ combine = word.substr(3);
+ }else{
+ combine += word;
+ }
+ continue;
+ }
// step2 combie phoneme to full word
{
int sub_word = !(word.find("@@") == string::npos);
--
Gitblit v1.9.1