| | |
|---|
| | | import torch |
|---|
| | | import torchaudio.compliance.kaldi as kaldi |
|---|
| | | from torch.nn.utils.rnn import pad_sequence |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | import funasr.models.frontend.eend_ola_feature as eend_ola_feature |
|---|
| | | from funasr.models.frontend.abs_frontend import AbsFrontend |
|---|
| | |
|---|
| | | rescale_line = line_item[3:(len(line_item) - 1)] |
|---|
| | | vars_list = list(rescale_line) |
|---|
| | | continue |
|---|
| | | means = np.array(means_list).astype(np.float) |
|---|
| | | vars = np.array(vars_list).astype(np.float) |
|---|
| | | means = np.array(means_list).astype(np.float32) |
|---|
| | | vars = np.array(vars_list).astype(np.float32) |
|---|
| | | cmvn = np.array([means, vars]) |
|---|
| | | cmvn = torch.as_tensor(cmvn, dtype=torch.float32) |
|---|
| | | return cmvn |
|---|
| | |
|---|
| | | snip_edges: bool = True, |
|---|
| | | upsacle_samples: bool = True, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__() |
|---|
| | | self.fs = fs |
|---|
| | | self.window = window |
|---|
| | |
|---|
| | | snip_edges: bool = True, |
|---|
| | | upsacle_samples: bool = True, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__() |
|---|
| | | self.fs = fs |
|---|
| | | self.window = window |
|---|
| | |
|---|
| | | return feats_pad, feats_lens, lfr_splice_frame_idxs |
|---|
| | | |
|---|
| | | def forward( |
|---|
| | | self, input: torch.Tensor, input_lengths: torch.Tensor, is_final: bool = False |
|---|
| | | self, input: torch.Tensor, input_lengths: torch.Tensor, is_final: bool = False, reset: bool = False |
|---|
| | | ) -> Tuple[torch.Tensor, torch.Tensor]: |
|---|
| | | if reset: |
|---|
| | | self.cache_reset() |
|---|
| | | batch_size = input.shape[0] |
|---|
| | | assert batch_size == 1, 'we support to extract feature online only when the batch size is equal to 1 now' |
|---|
| | | waveforms, feats, feats_lengths = self.forward_fbank(input, input_lengths) # input shape: B T D |
|---|
| | |
|---|
| | | lfr_m: int = 1, |
|---|
| | | lfr_n: int = 1, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__() |
|---|
| | | self.fs = fs |
|---|
| | | self.frame_length = frame_length |
|---|
| | |
|---|
| | | feats_pad = pad_sequence(feats, |
|---|
| | | batch_first=True, |
|---|
| | | padding_value=0.0) |
|---|
| | | return feats_pad, feats_lens |
|---|
| | | return feats_pad, feats_lens |
|---|
