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

update funasr.text -> funasr.tokenizer fix bug export

Browse Source
This commit is contained in:
游雁 2023-11-23 14:25:25 +08:00
parent 61567c6d3b
commit 68109d7458
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
funasr/models/frontend/wav_frontend.py
View File

@ -146,7 +146,7 @@ class WavFrontend(AbsFrontend):
feats_lens = torch.as_tensor(feats_lens) feats_lens = torch.as_tensor(feats_lens)
if batch_size == 1: if batch_size == 1:
feats_pad = feats[None, :, :] feats_pad = feats[0][None, :, :]
else: else:
feats_pad = pad_sequence(feats, feats_pad = pad_sequence(feats,
batch_first=True, batch_first=True,