speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

atsr

Browse Source
This commit is contained in:
语帆 2024-02-29 18:58:08 +08:00
parent 650c506cda
commit 84ad3e48a0
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
funasr/utils/load_utils.py
View File

@ -34,6 +34,7 @@ def load_audio_text_image_video(data_or_path_or_list, fs: int = 16000, audio_fs:
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)
pdb.set_trace()
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: