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

bugfix for paraformer-streaming

Browse Source
This commit is contained in:
游雁 2024-08-02 01:55:30 +08:00
parent 7f6099140a
commit a28de72b17
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
funasr/utils/load_utils.py
View File

@ -76,7 +76,7 @@ def load_audio_text_image_video(
for audio in data_or_path_or_list
]
if isinstance(data_or_path_or_list, str) and data_or_path_or_list.startswith(
("http://", "https://")
("http://", "https://")
): # download url to local file
data_or_path_or_list = download_from_url(data_or_path_or_list)
@ -112,7 +112,7 @@ def load_audio_text_image_video(
elif isinstance(data_or_path_or_list, str) and data_type == "text" and tokenizer is not None:
data_or_path_or_list = tokenizer.encode(data_or_path_or_list)
elif isinstance(data_or_path_or_list, np.ndarray): # audio sample point
data_or_path_or_list = torch.from_numpy(data_or_path_or_list).squeeze() # [n_samples,]
data_or_path_or_list = torch.from_numpy(data_or_path_or_list) # .squeeze() # [n_samples,]
elif isinstance(data_or_path_or_list, str) and data_type == "kaldi_ark":
data_mat = kaldiio.load_mat(data_or_path_or_list)
if isinstance(data_mat, tuple):