| | |
|---|
| | | token_num_int = torch.max(token_num).type(torch.int32).item()
|
|---|
| | | acoustic_embeds = acoustic_embeds[:, :token_num_int, :]
|
|---|
| | | return acoustic_embeds, token_num, alphas, cif_peak, token_num2
|
|---|
| | | |
|---|
| | | def get_upsample_timestamp(self, hidden, target_label=None, mask=None, ignore_id=-1, mask_chunk_predictor=None,
|
|---|
| | | target_label_length=None, token_num=None):
|
|---|
| | |
|
|---|
| | | def get_upsample_timestamp(self, hidden, mask=None, token_num=None):
|
|---|
| | | h = hidden
|
|---|
| | | b = hidden.shape[0]
|
|---|
| | | context = h.transpose(1, 2)
|
|---|
| | |
|---|
| | | mask_2 = torch.cat([ones_t, mask], dim=1)
|
|---|
| | | mask = mask_2 - mask_1
|
|---|
| | | tail_threshold = mask * tail_threshold
|
|---|
| | | alphas = torch.cat([alphas, tail_threshold], dim=1)
|
|---|
| | | alphas = torch.cat([alphas, zeros_t], dim=1)
|
|---|
| | | alphas = torch.add(alphas, tail_threshold)
|
|---|
| | | else:
|
|---|
| | | tail_threshold = torch.tensor([tail_threshold], dtype=alphas.dtype).to(alphas.device)
|
|---|
| | | tail_threshold = torch.reshape(tail_threshold, (1, 1))
|
|---|
