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

Browse Source
This commit is contained in:
speech_asr 2023-03-15 15:43:18 +08:00
parent e9f6703350
commit f691014c8a
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
funasr/models/frontend/wav_frontend.py
View File

@ -493,10 +493,10 @@ class WavFrontendMel23(AbsFrontend):
for i in range(batch_size):
waveform_length = input_lengths[i]
waveform = input[i][:waveform_length]
waveform = waveform.unsqueeze(0).numpy()
waveform = waveform.numpy()
mat = eend_ola_feature.stft(waveform, self.frame_length, self.frame_shift)
mat = eend_ola_feature.transform(mat)
mat = mat.splice(mat, context_size=self.lfr_m)
mat = eend_ola_feature.splice(mat, context_size=self.lfr_m)
mat = mat[::self.lfr_n]
mat = torch.from_numpy(mat)
feat_length = mat.size(0)