PaddleSpeech
PaddleSpeech copied to clipboard
跑kws demo 获取fbank时候总是卡在 AssertionError: choose a window size 400 that is [2, 1]
Others
feat_func = lambda waveform, sr: fbank(
waveform=paddle.to_tensor(waveform).unsqueeze(0),
sr=sr,
frame_shift=10,
frame_length=25,
n_mels=80)
keword_hi = feat_func(*paddleaudio.load('/home/test/nn_workspace/mine_keyword/hey_snips.wav'))
总是会报错 AssertionError: choose a window size 400 that is [2, 1]
这是版本
packaging 23.2 pypi_0 pypi
paddle-bfloat 0.1.7 pypi_0 pypi
paddle2onnx 1.2.11 pypi_0 pypi
paddleaudio 1.1.0 pypi_0 pypi
paddlefsl 1.1.0 pypi_0 pypi
paddlenlp 2.7.2 pypi_0 pypi
paddlepaddle-gpu 2.5.1 pypi_0 pypi
paddlesde 0.2.5 pypi_0 pypi
paddleslim 2.6.0 pypi_0 pypi
paddlespeech 0.0.0 pypi_0 pypi
paddlespeech-feat 0.1.0 pypi_0 pypi
pandas 2.2.3 pypi_0 pypi
parameterized 0.9.0 pypi_0 pypi
parso 0.8.4 pypi_0 pypi
pathos 0.2.8 pypi_0 pypi
pattern-singleton 1.2.0 pypi_0 pypi