| | |
|---|
| | | import numpy as np |
|---|
| | | import torch |
|---|
| | | import torchaudio.compliance.kaldi as kaldi |
|---|
| | | from funasr.models.frontend.abs_frontend import AbsFrontend |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | from torch.nn.utils.rnn import pad_sequence |
|---|
| | | |
|---|
| | | |
|---|
| | | # import kaldifeat |
|---|
| | | |
|---|
| | | def load_cmvn(cmvn_file): |
|---|
| | |
|---|
| | | means = np.array(means_list).astype(np.float) |
|---|
| | | vars = np.array(vars_list).astype(np.float) |
|---|
| | | cmvn = np.array([means, vars]) |
|---|
| | | cmvn = torch.as_tensor(cmvn) |
|---|
| | | return cmvn |
|---|
| | | |
|---|
| | | cmvn = torch.as_tensor(cmvn) |
|---|
| | | return cmvn |
|---|
| | | |
|---|
| | | |
|---|
| | | def apply_cmvn(inputs, cmvn_file): # noqa |
|---|
| | | """ |
|---|
| | |
|---|
| | | LFR_inputs.append(frame) |
|---|
| | | LFR_outputs = torch.vstack(LFR_inputs) |
|---|
| | | return LFR_outputs.type(torch.float32) |
|---|
| | | |
|---|
| | | |
|---|
| | | # class WavFrontend_kaldifeat(AbsFrontend): |
|---|
| | | # """Conventional frontend structure for ASR. |
|---|
| | |
|---|
| | | # feats_pad = pad_sequence(feats, |
|---|
| | | # batch_first=True, |
|---|
| | | # padding_value=0.0) |
|---|
| | | # return feats_pad, feats_lens |
|---|
| | | # return feats_pad, feats_lens |
|---|
