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

bug fix

Browse Source
This commit is contained in:
haoneng.lhn 2023-06-27 15:48:22 +08:00
parent a0defaf40e
commit 8042c51745
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/utils/wav_utils.py
View File

@ -189,9 +189,9 @@ def compute_fbank(wav_file,
def wav2num_frame(wav_path, frontend_conf):
try:
waveform, audio_sr = torchaudio.load(wav_file)
waveform, sampling_rate = torchaudio.load(wav_path)
except:
waveform, audio_sr = soundfile.read(wav_file)
waveform, sampling_rate = soundfile.read(wav_path)
waveform = torch.tensor(np.expand_dims(waveform, axis=0))
speech_length = (waveform.shape[1] / sampling_rate) * 1000.
n_frames = (waveform.shape[1] * 1000.0) / (sampling_rate * frontend_conf["frame_shift"] * frontend_conf["lfr_n"])