| | |
|---|
| | | |
|---|
| | | from funasr.modules.embedding import SinusoidalPositionEncoder |
|---|
| | | from funasr.models.encoder.sanm_encoder import SANMVadEncoder as Encoder |
|---|
| | | from funasr.train.abs_model import AbsPunctuation |
|---|
| | | |
|---|
| | | |
|---|
| | | class VadRealtimeTransformer(AbsPunctuation): |
|---|
| | | class VadRealtimeTransformer(torch.nn.Module): |
|---|
| | | """ |
|---|
| | | Author: Speech Lab, Alibaba Group, China |
|---|
| | | Author: Speech Lab of DAMO Academy, Alibaba Group |
|---|
| | | CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection |
|---|
| | | https://arxiv.org/pdf/2003.01309.pdf |
|---|
| | | """ |
|---|
