PaddlePaddle / PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
https://paddlespeech.readthedocs.io
Apache License 2.0
10.92k stars 1.83k forks source link

【KWS】AssertionError: choose a window size 400 that is [2, 1] #3124

Open Keyird opened 1 year ago

Keyird commented 1 year ago

Thank you for you work, but when I try the example of Keyword Spotting,there is a bug:

image

what's more,my codes is just from the example: https://aistudio.baidu.com/aistudio/projectdetail/5836435

` import paddleaudio from paddleaudio.compliance.kaldi import fbank

feat_func = lambda waveform, sr: fbank( waveform=paddle.to_tensor(waveform).unsqueeze(0), sr=sr, frame_shift=10, frame_length=25, n_mels=80)

keyword_feat = feat_func( paddleaudio.load('/home/aistudio/work/keyword.wav')) non_keyword_feat = feat_func( paddleaudio.load('/home/aistudio/work/non-keyword.wav')) `

zxcd commented 1 year ago

duplicate with https://github.com/PaddlePaddle/PaddleSpeech/issues/2644

liuying66 commented 1 year ago

同遇此问题,解决了吗

stale[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.