python/FunASR-XL.git

			@@ -11,7 +11,7 @@
			import numpy as np
			from funasr.modules.nets_utils import make_pad_mask
			from funasr.modules.attention import MultiHeadedAttention, MultiHeadedAttentionSANM, MultiHeadedAttentionSANMwithMask
			from funasr.modules.embedding import SinusoidalPositionEncoder
			from funasr.modules.embedding import SinusoidalPositionEncoder, StreamSinusoidalPositionEncoder
			from funasr.modules.layer_norm import LayerNorm
			from funasr.modules.multi_layer_conv import Conv1dLinear
			from funasr.modules.multi_layer_conv import MultiLayeredConv1d
			@@ -117,7 +117,7 @@

			class SANMEncoder(AbsEncoder):
			"""
			author: Speech Lab, Alibaba Group, China
			Author: Speech Lab of DAMO Academy, Alibaba Group
			San-m: Memory equipped self-attention for end-to-end speech recognition
			https://arxiv.org/abs/2006.01713

			@@ -180,6 +180,8 @@
			self.embed = torch.nn.Linear(input_size, output_size)
			elif input_layer == "pe":
			self.embed = SinusoidalPositionEncoder()
			elif input_layer == "pe_online":
			self.embed = StreamSinusoidalPositionEncoder()
			else:
			raise ValueError("unknown input_layer: " + input_layer)
			self.normalize_before = normalize_before
			@@ -357,7 +359,7 @@
			if self.embed is None:
			xs_pad = xs_pad
			else:
			xs_pad = self.embed.forward_chunk(xs_pad, cache)
			xs_pad = self.embed(xs_pad, cache)

			encoder_outs = self.encoders0(xs_pad, None, None, None, None)
			xs_pad, masks = encoder_outs[0], encoder_outs[1]
			@@ -549,7 +551,7 @@

			class SANMEncoderChunkOpt(AbsEncoder):
			"""
			author: Speech Lab, Alibaba Group, China
			Author: Speech Lab of DAMO Academy, Alibaba Group
			SCAMA: Streaming chunk-aware multihead attention for online end-to-end speech recognition
			https://arxiv.org/abs/2006.01713

			@@ -962,7 +964,7 @@

			class SANMVadEncoder(AbsEncoder):
			"""
			author: Speech Lab, Alibaba Group, China
			Author: Speech Lab of DAMO Academy, Alibaba Group

			"""