| | |
|---|
| | | |
|---|
| | | from funasr.modules.streaming_utils import utils as myutils |
|---|
| | | from funasr.models.decoder.transformer_decoder import BaseTransformerDecoder |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | from funasr.modules.attention import MultiHeadedAttentionSANMDecoder, MultiHeadedAttentionCrossAtt |
|---|
| | | from funasr.modules.embedding import PositionalEncoding |
|---|
| | |
|---|
| | | |
|---|
| | | class ContextualParaformerDecoder(ParaformerSANMDecoder): |
|---|
| | | """ |
|---|
| | | author: Speech Lab, Alibaba Group, China |
|---|
| | | Author: Speech Lab of DAMO Academy, Alibaba Group |
|---|
| | | Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition |
|---|
| | | https://arxiv.org/abs/2006.01713 |
|---|
| | | """ |
|---|
| | |
|---|
| | | kernel_size: int = 21, |
|---|
| | | sanm_shfit: int = 0, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__( |
|---|
| | | vocab_size=vocab_size, |
|---|
| | | encoder_output_size=encoder_output_size, |
|---|
