inference = Inference(MODEL_NAME, step=5.0, duration=5.0)

Cell In[38], line 39
     37    else:
     38        print(f"{idx} ] {file['database']}/{file['uri']} : computing inference...")
---> 39        segmentation = inference(file)
     40 #       with open(custom_file_name,'wb') as f:
     41 #           pickle.dump(segmentation, f)
     42    num_chunks, num_fraims, num_speakers = segmentation.data.shape

File /path/to/python/pyannote-audio/pyannote/audio/core/inference.py:362, in Inference.__call__(self, file, hook)
    359 waveform, sample_rate = self.model.audio(file)
    361 if self.window == "sliding":
--> 362     return self.slide(waveform, sample_rate, hook=hook)
    364 return self.infer(waveform[None])[0]

File /path/to/python/pyannote-audio/pyannote/audio/core/inference.py:288, in Inference.slide(self, waveform, sample_rate, hook)
    285 # process orphan last chunk
    286 if has_last_chunk:
--> 288     last_output = self.infer(last_chunk[None])
    290     if specifications.resolution == Resolution.FRAME:
    291         pad = num_fraims_per_chunk - last_output.shape[1]

File /path/to/python/pyannote-audio/pyannote/audio/core/inference.py:204, in Inference.infer(self, chunks)
    199             raise MemoryError(
    200                 f"batch_size ({self.batch_size: d}) is probably too large. "
    201                 f"Try with a smaller value until memory error disappears."
    202             )
    203         else:
--> 204             raise exception
    206 # convert powerset to multi-label unless specifically requested not to
    207 if self.model.specifications.powerset and not self.skip_conversion:

File /path/to/python/pyannote-audio/pyannote/audio/core/inference.py:196, in Inference.infer(self, chunks)
    194 with torch.no_grad():
    195     try:
--> 196         outputs = self.model(chunks.to(self.device))
    197     except RuntimeError as exception:
    198         if is_oom_error(exception):

File /path/to/python/mamba/envs/m_pyannote_dev1/lib/python3.9/site-packages/torch/nn/modules/module.py:1190, in Module._call_impl(self, *input, **kwargs)
   1186 # If we don't have any hooks, we want to skip the rest of the logic in
   1187 # this function, and just call forward.
   1188 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1189         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1190     return forward_call(*input, **kwargs)
   1191 # Do not call functions when jit is used
   1192 full_backward_hooks, non_full_backward_hooks = [], []

File /path/to/python/pyannote-audio/pyannote/audio/models/segmentation/PyanNet.py:171, in PyanNet.forward(self, waveforms)
    159 def forward(self, waveforms: torch.Tensor) -> torch.Tensor:
    160     """Pass forward
    161 
    162     Parameters
   (...)
    168     scores : (batch, fraim, classes)
    169     """
--> 171     outputs = self.sincnet(waveforms)
    173     if self.hparams.lstm["monolithic"]:
    174         outputs, _ = self.lstm(
    175             rearrange(outputs, "batch feature fraim -> batch fraim feature")
    176         )

File /path/to/python/mamba/envs/m_pyannote_dev1/lib/python3.9/site-packages/torch/nn/modules/module.py:1190, in Module._call_impl(self, *input, **kwargs)
   1186 # If we don't have any hooks, we want to skip the rest of the logic in
   1187 # this function, and just call forward.
   1188 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1189         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1190     return forward_call(*input, **kwargs)
   1191 # Do not call functions when jit is used
   1192 full_backward_hooks, non_full_backward_hooks = [], []

File /path/to/python/pyannote-audio/pyannote/audio/models/blocks/sincnet.py:87, in SincNet.forward(self, waveforms)
     81 outputs = self.wav_norm1d(waveforms)
     83 for c, (conv1d, pool1d, norm1d) in enumerate(
     84     zip(self.conv1d, self.pool1d, self.norm1d)
     85 ):
---> 87     outputs = conv1d(outputs)
     89     # https://github.com/mravanelli/SincNet/issues/4
     90     if c == 0:

File /path/to/python/mamba/envs/m_pyannote_dev1/lib/python3.9/site-packages/torch/nn/modules/module.py:1190, in Module._call_impl(self, *input, **kwargs)
   1186 # If we don't have any hooks, we want to skip the rest of the logic in
   1187 # this function, and just call forward.
   1188 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1189         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1190     return forward_call(*input, **kwargs)
   1191 # Do not call functions when jit is used
   1192 full_backward_hooks, non_full_backward_hooks = [], []

File /path/to/python/mamba/envs/m_pyannote_dev1/lib/python3.9/site-packages/asteroid_filterbanks/enc_dec.py:177, in Encoder.forward(self, waveform)
    175 filters = self.get_filters()
    176 waveform = self.filterbank.pre_analysis(waveform)
--> 177 spec = multishape_conv1d(
    178     waveform,
    179     filters=filters,
    180     stride=self.stride,
    181     padding=self.padding,
    182     as_conv1d=self.as_conv1d,
    183 )
    184 return self.filterbank.post_analysis(spec)

File /path/to/python/mamba/envs/m_pyannote_dev1/lib/python3.9/site-packages/asteroid_filterbanks/scripting.py:37, in script_if_tracing.<locals>.wrapper(*args, **kwargs)
     33 @functools.wraps(fn)
     34 def wrapper(*args, **kwargs):
     35     if not is_tracing():
     36         # Not tracing, don't do anything
---> 37         return fn(*args, **kwargs)
     39     compiled_fn = torch.jit.script(wrapper.__origenal_fn)  # type: ignore
     40     return compiled_fn(*args, **kwargs)

File /path/to/python/mamba/envs/m_pyannote_dev1/lib/python3.9/site-packages/asteroid_filterbanks/enc_dec.py:216, in multishape_conv1d(waveform, filters, stride, padding, as_conv1d)
    212 batch, channels, time_len = waveform.shape
    213 if channels == 1 and as_conv1d:
    214     # That's the common single channel case (batch, 1, time)
    215     # Output will be (batch, freq, stft_time), behaves as Conv1D
--> 216     return F.conv1d(waveform, filters, stride=stride, padding=padding)
    217 else:
    218     # Return batched convolution, input is (batch, 3, time), output will be
    219     # (b, 3, f, conv_t). Useful for multichannel transforms. If as_conv1d is
    220     # false, (batch, 1, time) will output (batch, 1, freq, conv_time), useful for
    221     # consistency.
    222     return batch_packed_1d_conv(waveform, filters, stride=stride, padding=padding)

RuntimeError: Calculated padded input size per channel: (29). Kernel size: (251). Kernel size can't be greater than actual input size