| | |
|---|
| | | fbanks, fbanks_len = self.frontend.forward_fbank(speech, speech_lengths) |
|---|
| | | feats, feats_len = self.frontend.forward_lfr_cmvn(fbanks, fbanks_len) |
|---|
| | | fbanks = to_device(fbanks, device=self.device) |
|---|
| | | # feats = to_device(feats, device=self.device) |
|---|
| | | feats = to_device(feats, device=self.device) |
|---|
| | | feats_len = feats_len.int() |
|---|
| | | else: |
|---|
| | | raise Exception("Need to extract feats first, please configure frontend configuration") |
|---|
| | |
|---|
| | | "in_cache": in_cache |
|---|
| | | } |
|---|
| | | # a. To device |
|---|
| | | batch = to_device(batch, device=self.device) |
|---|
| | | #batch = to_device(batch, device=self.device) |
|---|
| | | segments_part, in_cache = self.vad_model(**batch) |
|---|
| | | if segments_part: |
|---|
| | | for batch_num in range(0, self.batch_size): |
|---|
| | |
|---|
| | | 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, dype=torch.float32) |
|---|
| | | cmvn = torch.as_tensor(cmvn, dtype=torch.float32) |
|---|
| | | return cmvn |
|---|
| | | |
|---|
| | | |
|---|
