speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
speech_asr 2023-03-15 15:58:43 +08:00
parent 429ea5d378
commit fbec0f003d
2 changed files with 6 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
funasr/models/frontend/wav_frontend.py
View File

@ -11,8 +11,6 @@ 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:
@ -425,10 +423,8 @@ class WavFrontendOnline(AbsFrontend):
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 @@ class WavFrontendMel23(AbsFrontend):
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]

5
funasr/modules/eend_ola/encoder_decoder_attractor.py
View File

@ -2,7 +2,8 @@ import numpy as np
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 @@ class EncoderDecoderAttractor(nn.Module):
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)