Why I speend a whole night to load and initial the 70G file "Mandarin LM Large", it is not done yet ??
Created by: gangyahaidao
Hello, guys:
Now i want to to load the file "Mandarin LM Large" which is 70G size for ASR, but I speed the whole last night to init it, it has not done yet, Here is my load info output:
----------- Configuration Arguments -----------
alpha: 1.15
beam_size: 500
beta: 0.15
cutoff_prob: 1.0
cutoff_top_n: 40
decoding_method: ctc_beam_search
host_ip: localhost
host_port: 8086
lang_model_path: models/lm/zhidao_giga.klm
mean_std_path: models/aishell/mean_std.npz
model_path: models/aishell/params.tar.gz
num_conv_layers: 2
num_rnn_layers: 3
rnn_layer_size: 1024
share_rnn_weights: 0
specgram_type: linear
speech_save_dir: demo_cache
use_gpu: 1
use_gru: 1
vocab_path: models/aishell/vocab.txt
warmup_manifest: data/aishell/manifest.test
------------------------------------------------
I0420 00:18:23.264974 2271 Util.cpp:166] commandline: --use_gpu=1 --trainer_count=1
[INFO 2018-04-20 00:18:24,713 layers.py:2716] output for __conv_0__: c = 32, h = 81, w = 54, size = 139968
[INFO 2018-04-20 00:18:24,714 layers.py:3361] output for __batch_norm_0__: c = 32, h = 81, w = 54, size = 139968
[INFO 2018-04-20 00:18:24,715 layers.py:7533] output for __scale_sub_region_0__: c = 32, h = 81, w = 54, size = 139968
[INFO 2018-04-20 00:18:24,715 layers.py:2716] output for __conv_1__: c = 32, h = 41, w = 54, size = 70848
[INFO 2018-04-20 00:18:24,716 layers.py:3361] output for __batch_norm_1__: c = 32, h = 41, w = 54, size = 70848
[INFO 2018-04-20 00:18:24,716 layers.py:7533] output for __scale_sub_region_1__: c = 32, h = 41, w = 54, size = 70848
[INFO 2018-04-20 00:18:28,632 model.py:243] begin to initialize the external scorer for decoding
I don't known why, any help will appreciate?
this is my computer hardware info: 7.7 GiB Intel® Xeon(R) CPU E3-1231 v3 @ 3.40GHz × 8 GeForce GTX 1070/PCIe/SSE2