zyb8543d

synthetic speech pacing is very fast with frontend script

22

@Jackiexiao synthetic speech pacing is very fast, do you think what is the reason? how to solve it? 37050000 37800000 x^iou4-m+ei4=sh@/A:4-4^1@/B:25+4@2^1^26+5#26-5-/C:a_a^n#2+2+2&/D:xx=30!xx@1-1&/E:xx|30-xx@xx#1&xx!1-1#/F:xx^30=17_1-1! 37800000 38600000 iou4^m-ei4+sh=ih1@/A:4-4^1@/B:25+4@2^1^26+5#26-5-/C:a_a^n#2+2+2&/D:xx=30!xx@1-1&/E:xx|30-xx@xx#1&xx!1-1#/F:xx^30=17_1-1! 38600000 39750000 m^ei4-sh+ih1=y@/A:4-1^4@/B:26+3@1^2^27+4#27-4-/C:a_n^z#2+2+2&/D:xx=30!xx@1-1&/E:xx|30-xx@xx#1&xx!1-1#/F:xx^30=17_1-1! 39750000 40400000 ei4^sh-ih1+y=i4@/A:4-1^4@/B:26+3@1^2^27+4#27-4-/C:a_n^z#2+2+2&/D:xx=30!xx@1-1&/E:xx|30-xx@xx#1&xx!1-1#/F:xx^30=17_1-1!...

i run it on centos7 and python3.8.3，and i just want to run it on cpu not gpu. I met follows error： ``` >>> import nnsplit Traceback (most recent call last):...

decode speed is very slow on gpu

11

i use asr_inference.py and pretrained aishell model to decode on gpu，a 9.3s audio cost 6minutes to decode on gpu.

Support for decoding of TDNN-LSTM nnet3?

8

vosk api is defautly support for decoding of TDNN nnet3. I did some experiments, the TDNN-LSTM is obviously better than TDNN and the TDNN-LSTM get 3% gain comparing with TDNN....

Could NOT find BLAS

2

``` running install_lib running build_ext Using PYCLIF: /home/ybZhang/pykaldienv/bin/pyclif Using CLIF_MATCHER: /home/ybZhang/pykaldienv/clang/bin/clif-matcher -- Running gen_cmake_skeleton.py CMake Error at /usr/local/share/cmake-3.20/Modules/FindPackageHandleStandardArgs.cmake:230 (message): Could NOT find BLAS (missing: BLAS_LIBRARIES) Call Stack (most recent call...

errors about installing clif

6

when i run the script install_clif.sh , I get follows errors: `-- Generating done -- Build files have been written to: /home/ybZhang/pykaldi/tools/clif_backend/build_matcher [2/1786] Building CXX objec...port.dir/LineIterator.cpp.o FAILED: lib/Support/CMakeFiles/LLVMSupport.dir/LineIterator.cpp.o /usr/bin/g++ -std=c++11...

Adding punctuator for long text

1

convert an hours audio to text and add punctuator for long text ，I find that it becomes very slowlly and 2000% of memory

Chinese Synthetic speech pacing is very fast

6

synthetic speech pacing is very fast [B11_2.zip](https://github.com/CSTR-Edinburgh/merlin/files/2140731/B11_2.zip)

gpu decoding vs cpu decoding for libtorch

2

gpu decoding for libtorch is slow than cpu decoding on a same audio ， whether the speed of my test on cpu and gpu is normal？ ``` gpu decode： real...

angular-cli compiling

3

@nshmyrev I am using the angular-demo，so i must compiling the angular-cli，when i run yarn to install angular dependence，met follows errors，can give me some advice？thanks！ ``` yarn install v1.22.17 [1/5] Validating...