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

add support mixture of kaldi_ark or sound

Browse Source
This commit is contained in:
志浩 2024-09-24 20:09:30 +08:00
parent ef817d0a7d
commit 43af70b129
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
funasr/utils/load_utils.py
View File

@ -114,6 +114,9 @@ def load_audio_text_image_video(
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,]
elif isinstance(data_or_path_or_list, str) and data_type in ["kaldi_ark", "kaldi_ark_or_sound"]:
if len(data_or_path_or_list.split()) == 2:
data_or_path_or_list, audio_fs = data_or_path_or_list.split()
audio_fs = int(audio_fs)
data_mat = kaldiio.load_mat(data_or_path_or_list)
if isinstance(data_mat, tuple):
audio_fs, mat = data_mat