From 2c3183b61148c622a063edf686440673667c2ce2 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 23 一月 2024 11:16:34 +0800
Subject: [PATCH] Funasr1.0 (#1284)
---
funasr/models/ct_transformer/model.py | 3 ++-
funasr/utils/load_utils.py | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/funasr/models/ct_transformer/model.py b/funasr/models/ct_transformer/model.py
index 8c3f043..330d7e5 100644
--- a/funasr/models/ct_transformer/model.py
+++ b/funasr/models/ct_transformer/model.py
@@ -333,12 +333,13 @@
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]
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 punc_array is None:
punc_array = punctuations
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index 9cd3854..6f60dac 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -39,7 +39,8 @@
if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local file
if data_type is None or data_type == "sound":
data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list)
- data_or_path_or_list = data_or_path_or_list[0, :]
+ if kwargs.get("reduce_channels", True):
+ data_or_path_or_list = data_or_path_or_list.mean(0)
elif data_type == "text" and tokenizer is not None:
data_or_path_or_list = tokenizer.encode(data_or_path_or_list)
elif data_type == "image": # undo
--
Gitblit v1.9.1