From 831c48a886a5b879b46fc422cdc9c0898f6c34ec Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 15 一月 2024 11:07:33 +0800
Subject: [PATCH] download configuration.json
---
funasr/models/ct_transformer/model.py | 12 +++++++++---
1 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/funasr/models/ct_transformer/model.py b/funasr/models/ct_transformer/model.py
index fbf1804..7187f45 100644
--- a/funasr/models/ct_transformer/model.py
+++ b/funasr/models/ct_transformer/model.py
@@ -60,7 +60,7 @@
- def punc_forward(self, text: torch.Tensor, text_lengths: torch.Tensor) -> Tuple[torch.Tensor, None]:
+ def punc_forward(self, text: torch.Tensor, text_lengths: torch.Tensor, **kwargs):
"""Compute loss value from buffer sequences.
Args:
@@ -225,8 +225,14 @@
# text = data_in[0]
# text_lengths = data_lengths[0] if data_lengths is not None else None
split_size = kwargs.get("split_size", 20)
-
- tokens = split_words(text)
+
+ jieba_usr_dict = kwargs.get("jieba_usr_dict", None)
+ if jieba_usr_dict and isinstance(jieba_usr_dict, str):
+ import jieba
+ jieba.load_userdict(jieba_usr_dict)
+ jieba_usr_dict = jieba
+ kwargs["jieba_usr_dict"] = "jieba_usr_dict"
+ tokens = split_words(text, jieba_usr_dict=jieba_usr_dict)
tokens_int = tokenizer.encode(tokens)
mini_sentences = split_to_mini_sentence(tokens, split_size)
--
Gitblit v1.9.1