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 cross fade for 4o

Browse Source
This commit is contained in:
志浩 2024-09-18 16:44:24 +08:00
parent 8df772de10
commit c1a4abe273
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/llm_asr/tts_models/nar_acoustic_model.py
View File

@ -464,7 +464,7 @@ class NARCTCModel(nn.Module):
return_probs=True,
)
reduced_fa_tokens = []
for pred_token, pred_frame in itertools.groupby(fa_tokens.cpu().tolist()):
for pred_token, pred_frame in itertools.groupby(fa_tokens[0].cpu().tolist()):
if pred_token != 0:
reduced_fa_tokens.append(pred_token)
else: