update

speech_asr

2023-03-15 fbec0f003d4de9e4b6ccb6bb58d2d4926a0ff332

update

 funasr/models/frontend/wav_frontend.py

@@ -11,8 +11,6 @@
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:
@@ -425,10 +423,8 @@
                    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
@@ -487,9 +483,6 @@
        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]

 funasr/modules/eend_ola/encoder_decoder_attractor.py

@@ -2,7 +2,8 @@
import torch
import torch.nn.functional as F
from torch import nn

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

class EncoderDecoderAttractor(nn.Module):

@@ -16,7 +17,9 @@
        self.n_units = n_units

    def forward_core(self, xs, zeros):
        logger.info("xs: ".format(xs))
        ilens = torch.from_numpy(np.array([x.shape[0] for x in xs])).to(torch.float32).to(xs[0].device)
        logger.info("ilens: ".format(ilens))
        xs = [self.enc0_dropout(x) for x in xs]
        xs = nn.utils.rnn.pad_sequence(xs, batch_first=True, padding_value=-1)
        xs = nn.utils.rnn.pack_padded_sequence(xs, ilens, batch_first=True, enforce_sorted=False)