python/FunASR-XL.git

			@@ -95,7 +95,7 @@
			n_feat,
			dropout_rate,
			kernel_size,
			sanm_shift=0,
			sanm_shfit=0,
			lora_list=None,
			lora_rank=8,
			lora_alpha=16,
			@@ -121,17 +121,17 @@
			)
			# padding
			left_padding = (kernel_size - 1) // 2
			if sanm_shift > 0:
			left_padding = left_padding + sanm_shift
			if sanm_shfit > 0:
			left_padding = left_padding + sanm_shfit
			right_padding = kernel_size - 1 - left_padding
			self.pad_fn = nn.ConstantPad1d((left_padding, right_padding), 0.0)

			def forward_fsmn(self, inputs, mask, mask_shift_chunk=None):
			def forward_fsmn(self, inputs, mask, mask_shfit_chunk=None):
			b, t, d = inputs.size()
			if mask is not None:
			mask = torch.reshape(mask, (b, -1, 1))
			if mask_shift_chunk is not None:
			mask = mask * mask_shift_chunk
			if mask_shfit_chunk is not None:
			mask = mask * mask_shfit_chunk
			inputs = inputs * mask

			x = inputs.transpose(1, 2)
			@@ -211,7 +211,7 @@

			return self.linear_out(x) # (batch, time1, d_model)

			def forward(self, x, mask, mask_shift_chunk=None, mask_att_chunk_encoder=None):
			def forward(self, x, mask, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
			"""Compute scaled dot product attention.

			Args:
			@@ -226,7 +226,7 @@

			"""
			q_h, k_h, v_h, v = self.forward_qkv(x)
			fsmn_memory = self.forward_fsmn(v, mask, mask_shift_chunk)
			fsmn_memory = self.forward_fsmn(v, mask, mask_shfit_chunk)
			q_h = q_h * self.d_k ** (-0.5)
			scores = torch.matmul(q_h, k_h.transpose(-2, -1))
			att_outs = self.forward_attention(v_h, scores, mask, mask_att_chunk_encoder)
			@@ -326,7 +326,7 @@
			self.stochastic_depth_rate = stochastic_depth_rate
			self.dropout_rate = dropout_rate

			def forward(self, x, mask, cache=None, mask_shift_chunk=None, mask_att_chunk_encoder=None):
			def forward(self, x, mask, cache=None, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
			"""Compute encoded features.

			Args:
			@@ -363,7 +363,7 @@
			self.self_attn(
			x,
			mask,
			mask_shift_chunk=mask_shift_chunk,
			mask_shfit_chunk=mask_shfit_chunk,
			mask_att_chunk_encoder=mask_att_chunk_encoder,
			),
			),
			@@ -379,7 +379,7 @@
			self.self_attn(
			x,
			mask,
			mask_shift_chunk=mask_shift_chunk,
			mask_shfit_chunk=mask_shfit_chunk,
			mask_att_chunk_encoder=mask_att_chunk_encoder,
			)
			)
			@@ -388,7 +388,7 @@
			self.self_attn(
			x,
			mask,
			mask_shift_chunk=mask_shift_chunk,
			mask_shfit_chunk=mask_shfit_chunk,
			mask_att_chunk_encoder=mask_att_chunk_encoder,
			)
			)
			@@ -402,7 +402,7 @@
			if not self.normalize_before:
			x = self.norm2(x)

			return x, mask, cache, mask_shift_chunk, mask_att_chunk_encoder
			return x, mask, cache, mask_shfit_chunk, mask_att_chunk_encoder

			def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
			"""Compute encoded features.
			@@ -469,7 +469,7 @@
			positionwise_conv_kernel_size: int = 1,
			padding_idx: int = -1,
			kernel_size: int = 11,
			sanm_shift: int = 0,
			sanm_shfit: int = 0,
			selfattention_layer_type: str = "sanm",
			**kwargs,
			):
			@@ -494,7 +494,7 @@
			output_size,
			attention_dropout_rate,
			kernel_size,
			sanm_shift,
			sanm_shfit,
			)
			encoder_selfattn_layer_args = (
			attention_heads,
			@@ -502,7 +502,7 @@
			output_size,
			attention_dropout_rate,
			kernel_size,
			sanm_shift,
			sanm_shfit,
			)

			self.encoders0 = nn.ModuleList(