I wanted to see a demo of the project using the pre-trained model. But this error occurred:
2022-04-13 20:36:43 WARNING setup_logger(30) Removing existing handlers from HowlClient logger
2022-04-13 20:36:43,874 INFO setup_logger(54) Set up logger (HowlClient), output path: None
Using cache found in /home/adib/.cache/torch/hub/castorini_howl_master
2022-04-13 20:36:44.069002: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
2022-04-13 20:36:44 INFO _init_num_threads(157) NumExpr defaulting to 4 threads.
2022-04-13 20:36:45 INFO init(97) target hey is assigned to label 0
2022-04-13 20:36:45 INFO init(97) target fire is assigned to label 1
2022-04-13 20:36:45 INFO init(97) target fox is assigned to label 2
2022-04-13 20:36:45 INFO init(97) target [OOV] is assigned to label 3
ALSA lib pcm_dsnoop.c:638:(snd_pcm_dsnoop_open) unable to open slave
ALSA lib pcm_dmix.c:1075:(snd_pcm_dmix_open) unable to open slave
ALSA lib pcm.c:2660:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2660:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2660:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm_oss.c:377:(_snd_pcm_oss_open) Unknown field port
ALSA lib pcm_oss.c:377:(_snd_pcm_oss_open) Unknown field port
ALSA lib pcm_usb_stream.c:486:(_snd_pcm_usb_stream_open) Invalid type for card
ALSA lib pcm_usb_stream.c:486:(_snd_pcm_usb_stream_open) Invalid type for card
ALSA lib pcm_dmix.c:1075:(snd_pcm_dmix_open) unable to open slave
2022-04-13 20:36:45,478 INFO start(140) Starting Howl inference client...
torch.Size([8000])
torch.Size([1, 40, 41])
Traceback (most recent call last):
File "/home/adib/Projects/wake word detection/howl/howl/client/howl_client.py", line 95, in _on_audio
if self.engine.infer(inp):
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, kwargs)
File "/home/adib/Projects/wake word detection/howl/howl/model/inference.py", line 240, in infer
self.ingest_frame(window.squeeze(0), self.curr_time)
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, *kwargs)
File "/home/adib/Projects/wake word detection/howl/howl/model/inference.py", line 263, in ingest_frame
transformed_frame = self.zmuv(self.std(frame.unsqueeze(0)))
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(input, kwargs)
File "/home/adib/Projects/wake word detection/howl/howl/data/transform/transform.py", line 77, in forward
x = self.passthrough(x, kwargs)
File "/home/adib/Projects/wake word detection/howl/howl/data/transform/transform.py", line 241, in passthrough
return self._execute_op(self.spec_transform, audio, kwargs)
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, kwargs)
File "/home/adib/Projects/wake word detection/howl/howl/data/transform/transform.py", line 229, in _execute_op
if not deltas_only : logmels = op(audio).add(1e-7).log_().contiguous()
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, *kwargs)
File "/home/adib/anaconda3/lib/python3.8/site-packages/torchaudio/transforms.py", line 480, in forward
specgram = self.spectrogram(waveform)
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(input, kwargs)
File "/home/adib/anaconda3/lib/python3.8/site-packages/torchaudio/transforms.py", line 96, in forward
return F.spectrogram(
File "/home/adib/anaconda3/lib/python3.8/site-packages/torchaudio/functional/functional.py", line 91, in spectrogram
spec_f = torch.stft(
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/functional.py", line 578, in stft
input = F.pad(input.view(extended_shape), [pad, pad], pad_mode)
File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 4006, in _pad
return torch._C._nn.reflection_pad1d(input, pad)
RuntimeError: Argument #4: Padding size should be less than the corresponding input dimension, but got: padding (256, 256) at dimension 2 of input [1, 120, 41]
Traceback (most recent call last):
File "test.py", line 9, in
client.start().join()
File "/home/adib/Projects/wake word detection/howl/howl/client/howl_client.py", line 148, in join
time.sleep(0.04)
RuntimeError
I wanted to see a demo of the project using the pre-trained model. But this error occurred:
2022-04-13 20:36:43 WARNING setup_logger(30) Removing existing handlers from HowlClient logger 2022-04-13 20:36:43,874 INFO setup_logger(54) Set up logger (HowlClient), output path: None Using cache found in /home/adib/.cache/torch/hub/castorini_howl_master 2022-04-13 20:36:44.069002: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1 2022-04-13 20:36:44 INFO _init_num_threads(157) NumExpr defaulting to 4 threads. 2022-04-13 20:36:45 INFO init(97) target hey is assigned to label 0 2022-04-13 20:36:45 INFO init(97) target fire is assigned to label 1 2022-04-13 20:36:45 INFO init(97) target fox is assigned to label 2 2022-04-13 20:36:45 INFO init(97) target [OOV] is assigned to label 3 ALSA lib pcm_dsnoop.c:638:(snd_pcm_dsnoop_open) unable to open slave ALSA lib pcm_dmix.c:1075:(snd_pcm_dmix_open) unable to open slave ALSA lib pcm.c:2660:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear ALSA lib pcm.c:2660:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe ALSA lib pcm.c:2660:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side ALSA lib pcm_oss.c:377:(_snd_pcm_oss_open) Unknown field port ALSA lib pcm_oss.c:377:(_snd_pcm_oss_open) Unknown field port ALSA lib pcm_usb_stream.c:486:(_snd_pcm_usb_stream_open) Invalid type for card ALSA lib pcm_usb_stream.c:486:(_snd_pcm_usb_stream_open) Invalid type for card ALSA lib pcm_dmix.c:1075:(snd_pcm_dmix_open) unable to open slave 2022-04-13 20:36:45,478 INFO start(140) Starting Howl inference client... torch.Size([8000]) torch.Size([1, 40, 41]) Traceback (most recent call last): File "/home/adib/Projects/wake word detection/howl/howl/client/howl_client.py", line 95, in _on_audio if self.engine.infer(inp): File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, kwargs) File "/home/adib/Projects/wake word detection/howl/howl/model/inference.py", line 240, in infer self.ingest_frame(window.squeeze(0), self.curr_time) File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, *kwargs) File "/home/adib/Projects/wake word detection/howl/howl/model/inference.py", line 263, in ingest_frame transformed_frame = self.zmuv(self.std(frame.unsqueeze(0))) File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(input, kwargs) File "/home/adib/Projects/wake word detection/howl/howl/data/transform/transform.py", line 77, in forward x = self.passthrough(x, kwargs) File "/home/adib/Projects/wake word detection/howl/howl/data/transform/transform.py", line 241, in passthrough return self._execute_op(self.spec_transform, audio, kwargs) File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, kwargs) File "/home/adib/Projects/wake word detection/howl/howl/data/transform/transform.py", line 229, in _execute_op if not deltas_only : logmels = op(audio).add(1e-7).log_().contiguous() File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, *kwargs) File "/home/adib/anaconda3/lib/python3.8/site-packages/torchaudio/transforms.py", line 480, in forward specgram = self.spectrogram(waveform) File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(input, kwargs) File "/home/adib/anaconda3/lib/python3.8/site-packages/torchaudio/transforms.py", line 96, in forward return F.spectrogram( File "/home/adib/anaconda3/lib/python3.8/site-packages/torchaudio/functional/functional.py", line 91, in spectrogram spec_f = torch.stft( File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/functional.py", line 578, in stft input = F.pad(input.view(extended_shape), [pad, pad], pad_mode) File "/home/adib/anaconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 4006, in _pad return torch._C._nn.reflection_pad1d(input, pad) RuntimeError: Argument #4: Padding size should be less than the corresponding input dimension, but got: padding (256, 256) at dimension 2 of input [1, 120, 41] Traceback (most recent call last): File "test.py", line 9, in
client.start().join()
File "/home/adib/Projects/wake word detection/howl/howl/client/howl_client.py", line 148, in join
time.sleep(0.04)
RuntimeError
Do you know how can I solve it?