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 batch support for token extraction

Browse Source
This commit is contained in:
志浩 2024-09-24 17:45:55 +08:00
parent 4f96a06d13
commit c37e04ea49
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/sense_voice/model_small.py
View File

@ -2060,6 +2060,6 @@ class SenseVoiceL(nn.Module):
ark_writer = self.writer
if ark_writer is not None:
for k, v, l in zip(key, tokens.detach().cpu().numpy(), out_lens):
ark_writer(k, tokens[:l])
ark_writer(k, v[:l])
return results, meta_data