python/FunASR-XL.git

			@@ -6,13 +6,10 @@
			import torch
			import torchaudio.compliance.kaldi as kaldi
			from torch.nn.utils.rnn import pad_sequence
			from typeguard import check_argument_types

			import funasr.models.frontend.eend_ola_feature as eend_ola_feature
			from funasr.models.frontend.abs_frontend import AbsFrontend

			from modelscope.utils.logger import get_logger
			logger = get_logger()

			def load_cmvn(cmvn_file):
			with open(cmvn_file, 'r', encoding='utf-8') as f:
			@@ -33,14 +30,14 @@
			rescale_line = line_item[3:(len(line_item) - 1)]
			vars_list = list(rescale_line)
			continue
			means = np.array(means_list).astype(np.float)
			vars = np.array(vars_list).astype(np.float)
			means = np.array(means_list).astype(np.float32)
			vars = np.array(vars_list).astype(np.float32)
			cmvn = np.array([means, vars])
			cmvn = torch.as_tensor(cmvn)
			cmvn = torch.as_tensor(cmvn, dtype=torch.float32)
			return cmvn


			def apply_cmvn(inputs, cmvn_file): # noqa
			def apply_cmvn(inputs, cmvn): # noqa
			"""
			Apply CMVN with mvn data
			"""
			@@ -49,11 +46,10 @@
			dtype = inputs.dtype
			frame, dim = inputs.shape

			cmvn = load_cmvn(cmvn_file)
			means = np.tile(cmvn[0:1, :dim], (frame, 1))
			vars = np.tile(cmvn[1:2, :dim], (frame, 1))
			inputs += torch.from_numpy(means).type(dtype).to(device)
			inputs *= torch.from_numpy(vars).type(dtype).to(device)
			means = cmvn[0:1, :dim]
			vars = cmvn[1:2, :dim]
			inputs += means.to(device)
			inputs *= vars.to(device)

			return inputs.type(torch.float32)

			@@ -98,7 +94,6 @@
			snip_edges: bool = True,
			upsacle_samples: bool = True,
			):
			assert check_argument_types()
			super().__init__()
			self.fs = fs
			self.window = window
			@@ -113,6 +108,7 @@
			self.dither = dither
			self.snip_edges = snip_edges
			self.upsacle_samples = upsacle_samples
			self.cmvn = None if self.cmvn_file is None else load_cmvn(self.cmvn_file)

			def output_size(self) -> int:
			return self.n_mels * self.lfr_m
			@@ -142,8 +138,8 @@

			if self.lfr_m != 1 or self.lfr_n != 1:
			mat = apply_lfr(mat, self.lfr_m, self.lfr_n)
			if self.cmvn_file is not None:
			mat = apply_cmvn(mat, self.cmvn_file)
			if self.cmvn is not None:
			mat = apply_cmvn(mat, self.cmvn)
			feat_length = mat.size(0)
			feats.append(mat)
			feats_lens.append(feat_length)
			@@ -196,8 +192,8 @@
			mat = input[i, :input_lengths[i], :]
			if self.lfr_m != 1 or self.lfr_n != 1:
			mat = apply_lfr(mat, self.lfr_m, self.lfr_n)
			if self.cmvn_file is not None:
			mat = apply_cmvn(mat, self.cmvn_file)
			if self.cmvn is not None:
			mat = apply_cmvn(mat, self.cmvn)
			feat_length = mat.size(0)
			feats.append(mat)
			feats_lens.append(feat_length)
			@@ -229,7 +225,6 @@
			snip_edges: bool = True,
			upsacle_samples: bool = True,
			):
			assert check_argument_types()
			super().__init__()
			self.fs = fs
			self.window = window
			@@ -397,8 +392,10 @@
			return feats_pad, feats_lens, lfr_splice_frame_idxs

			def forward(
			self, input: torch.Tensor, input_lengths: torch.Tensor, is_final: bool = False
			self, input: torch.Tensor, input_lengths: torch.Tensor, is_final: bool = False, reset: bool = False
			) -> Tuple[torch.Tensor, torch.Tensor]:
			if reset:
			self.cache_reset()
			batch_size = input.shape[0]
			assert batch_size == 1, 'we support to extract feature online only when the batch size is equal to 1 now'
			waveforms, feats, feats_lengths = self.forward_fbank(input, input_lengths) # input shape: B T D
			@@ -425,10 +422,8 @@
			reserve_frame_idx = lfr_splice_frame_idxs[0] - minus_frame
			# print('reserve_frame_idx: ' + str(reserve_frame_idx))
			# print('frame_frame: ' + str(frame_from_waveforms))
			self.reserve_waveforms = self.waveforms[:,
			reserve_frame_idx * self.frame_shift_sample_length:frame_from_waveforms * self.frame_shift_sample_length]
			sample_length = (
			frame_from_waveforms - 1) * self.frame_shift_sample_length + self.frame_sample_length
			self.reserve_waveforms = self.waveforms[:, reserve_frame_idx * self.frame_shift_sample_length:frame_from_waveforms * self.frame_shift_sample_length]
			sample_length = (frame_from_waveforms - 1) * self.frame_shift_sample_length + self.frame_sample_length
			self.waveforms = self.waveforms[:, :sample_length]
			else:
			# update self.reserve_waveforms and self.lfr_splice_cache
			@@ -468,7 +463,6 @@
			lfr_m: int = 1,
			lfr_n: int = 1,
			):
			assert check_argument_types()
			super().__init__()
			self.fs = fs
			self.frame_length = frame_length
			@@ -487,9 +481,6 @@
			batch_size = input.size(0)
			feats = []
			feats_lens = []
			logger.info("batch_size: {}".format(batch_size))
			logger.info("input: {}".format(input))
			logger.info("input_lengths: {}".format(input_lengths))
			for i in range(batch_size):
			waveform_length = input_lengths[i]
			waveform = input[i][:waveform_length]