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

Merge pull request #14 from alibaba-damo-academy/dev

Browse Source 
wav
This commit is contained in:
zhifu gao 2022-12-12 21:32:36 +08:00 committed by GitHub
commit 22f0bd8265
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
funasr/bin/asr_inference_paraformer.py
View File

@ -197,9 +197,9 @@ class Speech2Text:
# data: (Nsamples,) -> (1, Nsamples)
# lengths: (1,)
if len(speech.size()) < 3:
speech = speech.unsqueeze(0).to(getattr(torch, self.dtype))
speech_lengths = speech.new_full([1], dtype=torch.long, fill_value=speech.size(1))
# if len(speech.size()) < 3:
# speech = speech.unsqueeze(0).to(getattr(torch, self.dtype))
# speech_lengths = speech.new_full([1], dtype=torch.long, fill_value=speech.size(1))
lfr_factor = max(1, (speech.size()[-1]//80)-1)
batch = {"speech": speech, "speech_lengths": speech_lengths}