From 4f8bce944e273e317cb84c7046ea514b9d958b4b Mon Sep 17 00:00:00 2001
From: zhuzizyf <42790740+zhuzizyf@users.noreply.github.com>
Date: 星期六, 22 四月 2023 14:54:49 +0800
Subject: [PATCH] Update FsmnVad.cc
---
funasr/bin/asr_inference_paraformer_vad.py | 14 +++++++++++++-
1 files changed, 13 insertions(+), 1 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_vad.py b/funasr/bin/asr_inference_paraformer_vad.py
index 78fc5f3..1548f9f 100644
--- a/funasr/bin/asr_inference_paraformer_vad.py
+++ b/funasr/bin/asr_inference_paraformer_vad.py
@@ -228,7 +228,19 @@
output_dir_v2: Optional[str] = None,
fs: dict = None,
param_dict: dict = None,
+ **kwargs,
):
+
+ hotword_list_or_file = None
+ if param_dict is not None:
+ hotword_list_or_file = param_dict.get('hotword')
+
+ if 'hotword' in kwargs:
+ hotword_list_or_file = kwargs['hotword']
+
+ if speech2text.hotword_list is None:
+ speech2text.hotword_list = speech2text.generate_hotwords_list(hotword_list_or_file)
+
# 3. Build data-iterator
if data_path_and_name_and_type is None and raw_inputs is not None:
if isinstance(raw_inputs, torch.Tensor):
@@ -326,7 +338,7 @@
ibest_writer["token"][key] = " ".join(token)
ibest_writer["token_int"][key] = " ".join(map(str, token_int))
ibest_writer["vad"][key] = "{}".format(vadsegments)
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
ibest_writer["text_with_punc"][key] = text_postprocessed_punc
if time_stamp_postprocessed is not None:
ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed)
--
Gitblit v1.9.1