ERROR (compute-mfcc-feats[5.1.0-41fd]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:exp/make_mfcc/train/utt2dur.10

kaldi-asr / kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

http://kaldi-asr.org

Other

14.25k stars 5.32k forks source link

ERROR (compute-mfcc-feats[5.1.0-41fd]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:exp/make_mfcc/train/utt2dur.10 #3433

Closed shipleyxie closed 5 years ago

shipleyxie commented 5 years ago

Step 1: install tool needed in tools, and enter src do 'make ', got this error

nclude"   -fpreprocessed -m64 -g -gdwarf-2 -o "feature-mfcc-cuda.o" "/tmp/tmpxft_0000717e_00000000-53_feature-mfcc-cuda.compute_30.ii" 
make[1]: Leaving directory '/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi/src/cudafeat'
Makefile:136: recipe for target 'cudafeat' failed
make: *** [cudafeat] Error 2`

my computer is 1080Ti with cuda 8.0.

do egs/aishel/v1

sh run.sh

got this report:

# compute-mfcc-feats --write-utt2dur=ark,t:exp/make_mfcc/train/utt2dur.10 --verbose=2 --config=conf/mfcc.conf scp,p:exp/make_mfcc/train/wav_train.10.scp ark:- | copy-feats --write-num-frames=ark,t:exp/make_mfcc/train/utt2num_frames.10 --compress=true ark:- ark,scp:/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi/egs/aishell/v1/mfcc/raw_mfcc_train.10.ark,/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi/egs/aishell/v1/mfcc/raw_mfcc_train.10.scp 
# Started at Sat Jun 29 12:15:00 CST 2019
#
copy-feats --write-num-frames=ark,t:exp/make_mfcc/train/utt2num_frames.10 --compress=true ark:- ark,scp:/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi/egs/aishell/v1/mfcc/raw_mfcc_train.10.ark,/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi/egs/aishell/v1/mfcc/raw_mfcc_train.10.scp 

Create MFCC feature files.
Usage:  compute-mfcc-feats [options...] <wav-rspecifier> <feats-wspecifier>

Options:
  --blackman-coeff            : Constant coefficient for generalized Blackman window. (float, default = 0.42)
  --cepstral-lifter           : Constant that controls scaling of MFCCs (float, default = 22)
  --channel                   : Channel to extract (-1 -> expect mono, 0 -> left, 1 -> right) (int, default = -1)
  --debug-mel                 : Print out debugging information for mel bin computation (bool, default = false)
  --dither                    : Dithering constant (0.0 means no dither) (float, default = 1)
  --energy-floor              : Floor on energy (absolute, not relative) in MFCC computation (float, default = 0)
  --frame-length              : Frame length in milliseconds (float, default = 25)
  --frame-shift               : Frame shift in milliseconds (float, default = 10)
  --high-freq                 : High cutoff frequency for mel bins (if < 0, offset from Nyquist) (float, default = 0)
  --htk-compat                : If true, put energy or C0 last and use a factor of sqrt(2) on C0.  Warning: not sufficient to get HTK compatible features (need to change other parameters). (bool, default = false)
  --low-freq                  : Low cutoff frequency for mel bins (float, default = 20)
  --min-duration              : Minimum duration of segments to process (in seconds). (float, default = 0)
  --num-ceps                  : Number of cepstra in MFCC computation (including C0) (int, default = 13)
  --num-mel-bins              : Number of triangular mel-frequency bins (int, default = 23)
  --output-format             : Format of the output files [kaldi, htk] (string, default = "kaldi")
  --preemphasis-coefficient   : Coefficient for use in signal preemphasis (float, default = 0.97)
  --raw-energy                : If true, compute energy before preemphasis and windowing (bool, default = true)
  --remove-dc-offset          : Subtract mean from waveform on each frame (bool, default = true)
  --round-to-power-of-two     : If true, round window size to power of two. (bool, default = true)
  --sample-frequency          : Waveform data sample frequency (must match the waveform file, if specified there) (float, default = 16000)
  --snip-edges                : If true, end effects will be handled by outputting only frames that completely fit in the file, and the number of frames depends on the frame-length.  If false, the number of frames depends only on the frame-shift, and we reflect the data at the ends. (bool, default = true)
  --subtract-mean             : Subtract mean of each feature file [CMS]; not recommended to do it this way.  (bool, default = false)
  --use-energy                : Use energy (not C0) in MFCC computation (bool, default = true)
  --utt2spk                   : Utterance to speaker-id map rspecifier (if doing VTLN and you have warps per speaker) (string, default = "")
  --vtln-high                 : High inflection point in piecewise linear VTLN warping function (if negative, offset from high-mel-freq (float, default = -500)
  --vtln-low                  : Low inflection point in piecewise linear VTLN warping function (float, default = 100)
  --vtln-map                  : Map from utterance or speaker-id to vtln warp factor (rspecifier) (string, default = "")
  --vtln-warp                 : Vtln warp factor (only applicable if vtln-map not specified) (float, default = 1)
  --window-type               : Type of window ("hamming"|"hanning"|"povey"|"rectangular"|"blackmann") (string, default = "povey")

Standard options:
  --config                    : Configuration file to read (this option may be repeated) (string, default = "")
  --help                      : Print out usage message (bool, default = false)
  --print-args                : Print the command line arguments (to stderr) (bool, default = true)
  --verbose                   : Verbose level (higher->more logging) (int, default = 0)

Command line was: compute-mfcc-feats --write-utt2dur=ark,t:exp/make_mfcc/train/utt2dur.10 --verbose=2 --config=conf/mfcc.conf scp,p:exp/make_mfcc/train/wav_train.10.scp ark:- 
ERROR (compute-mfcc-feats[5.1.0-41fd]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:exp/make_mfcc/train/utt2dur.10

[ Stack-Trace: ]

kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*)
kaldi::MessageLogger::~MessageLogger()
kaldi::ParseOptions::Read(int, char const* const*)
main
__libc_start_main
compute-mfcc-feats() [0x42d409]

LOG (copy-feats[5.1.0-41fd]:main():copy-feats.cc:120) Copied 0 feature matrices.
# Accounting: time=0 threads=1
# Ended (code 1) at Sat Jun 29 12:15:00 CST 2019, elapsed time 0 seconds

danpovey commented 5 years ago

The error is likely because the files in featbin were not recompiled. About the make error with cudafeat, you need to show more of the output of make, else I won't know what the problem is. Also grep for CUDA in kaldi.mk and show me the output, and show the output of nvcc --version.

kkm000 commented 5 years ago

FWIW, I also got a trouble compiling cudafeat from the tip of the master branch on 06/26 with CUDA 10.1. I haven't look into it, sorry, just disabled it, was in a rush. I can try again on Monday in the afternoon, when I get to my keyboard.

shipleyxie commented 5 years ago

make in tools ......Success!
./configure enter src , and
make depend -j 8
make -j 8 got Error
**Makefile:136: recipe for target 'cudafeat' failed make: * [cudafeat] Error 2 The detail log is in enter_src_make_report.log

$grep -n cuda kaldi.mk 96:CUDATKDIR = /usr/local/cuda 115:CUDA_LDLIBS += -lcublas -lcusparse -lcudart -lcurand -lcufft -lnvToolsExt #LDLIBS : The .so libs are loaded later than static libs in implicit rule

hope there is a soulution to solve this...

danpovey commented 5 years ago

/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../thread/../thread/thread_operato
rs.cuh(115): error: calling a __device__ function("operator+") from a __host__ __device__ function("operator()") is not allowed
          detected during:
            instantiation of "T cub::Sum::operator()(const T &, const T &) const [with T=float2]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(143): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::ScanStep<HAS_IDENTITY,STEP,ScanOp>(T &, ScanOp, cub::Int2Type<STEP>) [with T=float2, 
LOGICAL_WARP_THREADS=32, PTX_ARCH=0, HAS_IDENTITY=false, STEP=0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(190): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, cub::Int2Type<IS_PRIMITIVE>) [with T=float2, LOGICAL_WA
RP_THREADS=32, PTX_ARCH=0, ScanOp=cub::Sum, IS_PRIMITIVE=0]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(229): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, Sc
anOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(241): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=
0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/warp_scan.cuh(503): here
            instantiation of "void cub::WarpScan<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, S
canOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/block_sca
n_raking.cuh(557): here
            instantiation of "void cub::BlockScanRaking<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, MEMOIZE, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK
_DIM_X=1024, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, MEMOIZE=false, PTX_ARCH=0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1766): her
e
            instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK_DIM
_X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1329): her
e
            instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveSum(T, T &, T &) [with T=float2, BLOCK_DIM_X=1024, 
ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0]" 
feature-online-cmvn-cuda.cu(65): here

danpovey commented 5 years ago

@luitjens @hugovbraun the errors are i my previous comment. Some kind of compilation error relating to cub? @shipleyxie @kkm000 I would accept a PR to just remove cudafeat and cudafeatbin from the compilation for the time being, as a temporary patch.

danpovey commented 5 years ago

Actually forget the thing about removing cudafeat and cudafeatbin, it would be necessary to remove cudadecoder and cudadecoderbin as well. Likely a newer CUDA toolkit would solve this, but I don't like having to require that. For now you could just remove all the cuda* directories from the Makefile and just compile the rest, as a workaround.

luitjens commented 5 years ago

I think this will fix the cub build issue:

https://github.com/kaldi-asr/kaldi/pull/3441

luitjens commented 5 years ago

@shipleyxie thanks for the full output of the build. That is very useful for tracking these issues down. Please update to the latest and see if the issue goes away.

Thanks, Justin

shipleyxie commented 5 years ago

follow your instruction, i can make in src Success! but when run egs/yesno got this Error, make me confused. ()

Preparing train and test data cp: cannot stat '../../input/task.arpabo': No such file or directory cp: cannot stat 'input/lexicon_nosil.txt': No such file or directory cp: cannot stat 'input/lexicon.txt': No such file or directory cat: input/phones.txt: No such file or directory Dictionary preparation succeeded utils/prepare_lang.sh --position-dependent-phones false data/local/dict data/local/lang data/lang Checking data/local/dict/silence_phones.txt ... --> reading data/local/dict/silence_phones.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ... --> reading data/local/dict/optional_silence.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ... --> ERROR: data/local/dict/nonsilence_phones.txt is empty or not exists Error validating directory data/local/dict Here<<<<<<<<<<<<<<<< Preparing language models for test arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test_tg/words.txt input/task.arpabo data/lang_test_tg/G.fst ERROR (arpa2fst[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/words.txt

[ Stack-Trace: ] arpa2fst(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4b5e68] arpa2fst(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x434be5] arpa2fst(kaldi::Input::Input(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x44dc34] arpa2fst(main+0x5a1) [0x432ff7] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f9e237c9830] arpa2fst(_start+0x29) [0x432989]

kaldi::KaldiFatalErrorfstisstochastic data/lang_test_tg/G.fst ERROR (fstisstochastic[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/G.fst

[ Stack-Trace: ] fstisstochastic(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4c3df4] fstisstochastic(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x43caad] fstisstochastic(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x454c4c] fstisstochastic(fst::ReadFstKaldiGeneric(std::cxx11::basic_string<char, std::char_traits, std::allocator >, bool)+0x71) [0x4478e2] fstisstochastic(main+0x227) [0x43b99d] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f6ad9b5c830] fstisstochastic(_start+0x29) [0x43b6a9]

kaldi::KaldiFatalErrorlocal/prepare_lm.sh: line 29: data/local/dict/lexicon.txt: No such file or directory ERROR: fstcompile: Open failed, file = tmpdir.g/select_empty.fst.txt ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: tmpdir.g/empty_words.fst Succeeded in formatting data. steps/make_mfcc.sh --nj 1 data/train_yesno exp/make_mfcc/train_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/train_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: Succeeded creating MFCC features for train_yesno steps/compute_cmvn_stats.sh data/train_yesno exp/make_mfcc/train_yesno mfcc Succeeded creating CMVN stats for train_yesno fix_data_dir.sh: kept all 31 utterances. fix_data_dir.sh: old files are kept in data/train_yesno/.backup steps/make_mfcc.sh --nj 1 data/test_yesno exp/make_mfcc/test_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/test_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (29 != 31); consider using utils/fix_data_dir.sh data/test_yesno steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error. steps/compute_cmvn_stats.sh data/test_yesno exp/make_mfcc/test_yesno mfcc Succeeded creating CMVN stats for test_yesno fix_data_dir.sh: kept 29 utterances out of 31 fix_data_dir.sh: old files are kept in data/test_yesno/.backup steps/train_mono.sh --nj 1 --cmd utils/run.pl --totgauss 400 data/train_yesno data/lang exp/mono0a cat: data/lang/oov.int: No such file or directory mkgraph.sh: expected data/lang_test_tg/L.fst to exist steps/decode.sh --nj 1 --cmd utils/run.pl exp/mono0a/graph_tgpr data/test_yesno exp/mono0a/decode_test_yesno steps/decode.sh: Error: no such file exp/mono0a/final.mdl grep: exp/mono0a/decode_testyesno/wer*: No such file or directory

danpovey commented 5 years ago

I suspect you changed the repository somehow. That file ../../input/task.arpabo is part of the repo. Do "git status" at top level to see what you changed or deleted.

On Wed, Jul 3, 2019 at 9:49 PM shipleyxie notifications@github.com wrote:

follow your instruction, i can make in src Success! but when run egs/yesno got this Error, make me confused. ()

Preparing train and test data cp: cannot stat '../../input/task.arpabo': No such file or directory cp: cannot stat 'input/lexicon_nosil.txt': No such file or directory cp: cannot stat 'input/lexicon.txt': No such file or directory cat: input/phones.txt: No such file or directory Dictionary preparation succeeded utils/prepare_lang.sh --position-dependent-phones false data/local/dict data/local/lang data/lang Checking data/local/dict/silence_phones.txt ... --> reading data/local/dict/silence_phones.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ... --> reading data/local/dict/optional_silence.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ... --> ERROR: data/local/dict/nonsilence_phones.txt is empty or not exists Error validating directory data/local/dict Here<<<<<<<<<<<<<<<< Preparing language models for test arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test_tg/words.txt input/task.arpabo data/lang_test_tg/G.fst ERROR (arpa2fst[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/words.txt

[ Stack-Trace: ] arpa2fst(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4b5e68] arpa2fst(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x434be5] arpa2fst(kaldi::Input::Input(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x44dc34] arpa2fst(main+0x5a1) [0x432ff7] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f9e237c9830] arpa2fst(_start+0x29) [0x432989]

kaldi::KaldiFatalErrorfstisstochastic data/lang_test_tg/G.fst ERROR (fstisstochastic[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/G.fst

[ Stack-Trace: ] fstisstochastic(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4c3df4] fstisstochastic(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x43caad] fstisstochastic(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x454c4c] fstisstochastic(fst::ReadFstKaldiGeneric(std::cxx11::basic_string<char, std::char_traits, std::allocator >, bool)+0x71) [0x4478e2] fstisstochastic(main+0x227) [0x43b99d] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f6ad9b5c830] fstisstochastic(_start+0x29) [0x43b6a9]

kaldi::KaldiFatalErrorlocal/prepare_lm.sh: line 29: data/local/dict/lexicon.txt: No such file or directory ERROR: fstcompile: Open failed, file = tmpdir.g/select_empty.fst.txt ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: tmpdir.g/empty_words.fst Succeeded in formatting data. steps/make_mfcc.sh --nj 1 data/train_yesno exp/make_mfcc/train_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/train_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: Succeeded creating MFCC features for train_yesno steps/compute_cmvn_stats.sh data/train_yesno exp/make_mfcc/train_yesno mfcc Succeeded creating CMVN stats for train_yesno fix_data_dir.sh: kept all 31 utterances. fix_data_dir.sh: old files are kept in data/train_yesno/.backup steps/make_mfcc.sh --nj 1 data/test_yesno exp/make_mfcc/test_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/test_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (29 != 31); consider using utils/fix_data_dir.sh data/test_yesno steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error. steps/compute_cmvn_stats.sh data/test_yesno exp/make_mfcc/test_yesno mfcc Succeeded creating CMVN stats for test_yesno fix_data_dir.sh: kept 29 utterances out of 31 fix_data_dir.sh: old files are kept in data/test_yesno/.backup steps/train_mono.sh --nj 1 --cmd utils/run.pl --totgauss 400 data/train_yesno data/lang exp/mono0a cat: data/lang/oov.int: No such file or directory mkgraph.sh: expected data/lang_test_tg/L.fst to exist steps/decode.sh --nj 1 --cmd utils/run.pl exp/mono0a/graph_tgpr data/test_yesno exp/mono0a/decode_test_yesno steps/decode.sh: Error: no such file exp/mono0a/final.mdl grep: exp/mono0a/decode_testyesno/wer*: No such file or directory

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/3433?email_source=notifications&email_token=AAZFLOYPPRAWGO5QXALF6VLP5VJLRA5CNFSM4H4JXIB2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZGCYII#issuecomment-508308513, or mute the thread https://github.com/notifications/unsubscribe-auth/AAZFLO5XAZTEOL3X4JWYQRDP5VJLRANCNFSM4H4JXIBQ .

benoriol commented 5 years ago

I am getting a similar error. When computing MFCC features. I get a similiar error to the one you commented.

`# paste-feats --length-tolerance=2 "ark:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- |
compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |" " ark,s,cs:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats -- verbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- |" ark:- | copy-feats --compress=true --write-num-frames=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfc c/log/utt2num_frames.1 ark:- ark,scp:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1.ark,/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1. scp # paste-feats --length-tolerance=2 'ark:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- |
compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |' 'ar k,s,cs:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats --ve rbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- |' ark:- copy-feats --compress=true --write-num-frames=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2num_frames.1 ark:- ark,scp:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw _mfcc_pitch_mfcc.1.ark,/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1.scp extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:-

Create MFCC feature files. Usage: compute-mfcc-feats [options...]

Options: --allow-downsample : If true, allow the input waveform to have a higher frequency than the specified --sample-frequency (and we'll downsample). (bool, default = false) --blackman-coeff : Constant coefficient for generalized Blackman window. (float, default = 0.42) ......................... ......................... ......................... Standard options: --config : Configuration file to read (this option may be repeated) (string, default = "") --help : Print out usage message (bool, default = false) --print-args : Print the command line arguments (to stderr) (bool, default = true) --verbose : Verbose level (higher->more logging) (int, default = 0)

Command line was: compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ar k:- ERROR (compute-mfcc-feats[5.5.93~1418-faa1f]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const) kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::ParseOptions::Read(int, char const const*) main __libc_start_main compute-mfcc-feats() [0x433d89]

ERROR (compute-mfcc-feats[5.5.93~1418-faa1f]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const) kaldi::MessageLogger::~MessageLogger() kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::ParseOptions::Read(int, char const const*) main __libc_start_main compute-mfcc-feats() [0x433d89]

extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- process-kaldi-pitch-feats ark:- ark:- compute-kaldi-pitch-feats --verbose=2 --config=conf/pitch.conf ark:- ark:- LOG (extract-segments[5.5.93~1418-faa1f]:main():extract-segments.cc:193) Successfully processed 3 lines out of 3 in the segments file. WARNING (paste-feats[5.5.93~1418-faa1f]:Close():kaldi-io.cc:515) Pipe extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train /mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats --verbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- | had nonzero return status 36096 LOG (paste-feats[5.5.93~1418-faa1f]:main():paste-feats.cc:158) Done 0 utts, errors on 0 WARNING (paste-feats[5.5.93~1418-faa1f]:Close():kaldi-io.cc:515) Pipe extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train /mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/c onf/mfcc.conf ark:- ark:- | had nonzero return status 65280 ERROR (paste-feats[5.5.93~1418-faa1f]:~SequentialTableReaderArchiveImpl():util/kaldi-table-inl.h:678) TableReader: error detected closing archive 'extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data- benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/l og/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |'

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*) kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix > >::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix > >::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReader<kaldi::KaldiObjectHolder<kaldi::Matrix > >::~SequentialTableReader() main __libc_start_main paste-feats() [0x42ddd9]

ERROR (paste-feats[5.5.93~1418-faa1f]:~SequentialTableReaderArchiveImpl():util/kaldi-table-inl.h:678) TableReader: error detected closing archive 'extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data- benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/l og/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |'

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*) kaldi::MessageLogger::~MessageLogger() kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix > >::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix > >::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReader<kaldi::KaldiObjectHolder<kaldi::Matrix > >::~SequentialTableReader() main __libc_start_main paste-feats() [0x42ddd9]

terminate called after throwing an instance of 'std::runtime_error' what():
LOG (copy-feats[5.5.93~1418-faa1f]:main():copy-feats.cc:143) Copied 0 feature matrices. # Accounting: time=1 threads=1 # Ended (code 1) at Mon Jul 8 10:29:43 CEST 2019, elapsed time 1 seconds

naxingyu commented 5 years ago

checkout the usage by calling src/featbin/compute-mfcc-feats If --write-utt2dur is not an option, pull and re-compile.

On Mon, Jul 8, 2019 at 5:17 PM benoriol notifications@github.com wrote:

I am getting a similar error. When computing MFCC features. I get a similiar error to the one you commented. paste-feats --length-tolerance=2 "ark:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- |

compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |" " ark,s,cs:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats -- verbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- |" ark:- | copy-feats --compress=true --write-num-frames=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfc c/log/utt2num_frames.1 ark:- ark,scp:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1.ark,/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1. scp

paste-feats --length-tolerance=2 'ark:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |' 'ar k,s,cs:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats --ve rbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- |' ark:- copy-feats --compress=true --write-num-frames=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2num_frames.1 ark:- ark,scp:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw

_mfcc_pitch_mfcc.1.ark,/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1.scp extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:-

Create MFCC feature files. Usage: compute-mfcc-feats [options...]

Options: --allow-downsample : If true, allow the input waveform to have a higher frequency than the specified --sample-frequency (and we'll downsample). (bool, default = false) --blackman-coeff : Constant coefficient for generalized Blackman window. (float, default = 0.42) ......................... ......................... ......................... Standard options: --config : Configuration file to read (this option may be repeated) (string, default = "") --help : Print out usage message (bool, default = false) --print-args : Print the command line arguments (to stderr) (bool, default = true) --verbose : Verbose level (higher->more logging) (int, default = 0)

Command line was: compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ar k:- ERROR (compute-mfcc-feats[5.5.93~1418-faa1f]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const) kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::ParseOptions::Read(int, char const const*) main __libc_start_main compute-mfcc-feats() [0x433d89]

ERROR (compute-mfcc-feats[5.5.93~1418-faa1f]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const) kaldi::MessageLogger::~MessageLogger() kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::ParseOptions::Read(int, char const const*) main __libc_start_main compute-mfcc-feats() [0x433d89]

extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- process-kaldi-pitch-feats ark:- ark:- compute-kaldi-pitch-feats --verbose=2 --config=conf/pitch.conf ark:- ark:- LOG (extract-segments[5.5.931418-faa1f]:main():extract-segments.cc:193) Successfully processed 3 lines out of 3 in the segments file. WARNING (paste-feats[5.5.931418-faa1f]:Close():kaldi-io.cc:515) Pipe extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train /mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats --verbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- | had nonzero return status 36096 LOG (paste-feats[5.5.931418-faa1f]:main():paste-feats.cc:158) Done 0 utts, errors on 0 WARNING (paste-feats[5.5.931418-faa1f]:Close():kaldi-io.cc:515) Pipe extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train /mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/c onf/mfcc.conf ark:- ark:- | had nonzero return status 65280 ERROR (paste-feats[5.5.93~1418-faa1f]:~SequentialTableReaderArchiveImpl():util/kaldi-table-inl.h:678) TableReader: error detected closing archive 'extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data- benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/l og/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |'

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*) kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix

::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix ::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReader<kaldi::KaldiObjectHolder ::~SequentialTableReader() main __libc_start_main paste-feats() [0x42ddd9]

ERROR (paste-feats[5.5.93~1418-faa1f]:~SequentialTableReaderArchiveImpl():util/kaldi-table-inl.h:678) TableReader: error detected closing archive 'extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data- benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/l og/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |'

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*) kaldi::MessageLogger::~MessageLogger() kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix

::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix ::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReader<kaldi::KaldiObjectHolder ::~SequentialTableReader() main __libc_start_main paste-feats() [0x42ddd9]

terminate called after throwing an instance of 'std::runtime_error' what(): LOG (copy-feats[5.5.93~1418-faa1f]:main():copy-feats.cc:143) Copied 0 feature matrices. Accounting: time=1 threads=1 Ended (code 1) at Mon Jul 8 10:29:43 CEST 2019, elapsed time 1 seconds

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/3433?email_source=notifications&email_token=AAZKTRCMA55442UM6U7ZRSDP6MA4JA5CNFSM4H4JXIB2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZMPVGI#issuecomment-509147801, or mute the thread https://github.com/notifications/unsubscribe-auth/AAZKTRCDSDDY5ZBUOWPHYRDP6MA4JANCNFSM4H4JXIBQ .

benoriol commented 5 years ago

I think it wasn't compiled correctly. It is solved now. Thanks!

Esdsnqxz commented 5 years ago

follow your instruction, i can make in src Success! but when run egs/yesno got this Error, make me confused. ()

Preparing train and test data cp: cannot stat '../../input/task.arpabo': No such file or directory cp: cannot stat 'input/lexicon_nosil.txt': No such file or directory cp: cannot stat 'input/lexicon.txt': No such file or directory cat: input/phones.txt: No such file or directory Dictionary preparation succeeded utils/prepare_lang.sh --position-dependent-phones false data/local/dict data/local/lang data/lang Checking data/local/dict/silence_phones.txt ... --> reading data/local/dict/silence_phones.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ... --> reading data/local/dict/optional_silence.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ... --> ERROR: data/local/dict/nonsilence_phones.txt is empty or not exists Error validating directory data/local/dict Here<<<<<<<<<<<<<<<< Preparing language models for test arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test_tg/words.txt input/task.arpabo data/lang_test_tg/G.fst ERROR (arpa2fst[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/words.txt

[ Stack-Trace: ] arpa2fst(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4b5e68] arpa2fst(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x434be5] arpa2fst(kaldi::Input::Input(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x44dc34] arpa2fst(main+0x5a1) [0x432ff7] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f9e237c9830] arpa2fst(_start+0x29) [0x432989]

kaldi::KaldiFatalErrorfstisstochastic data/lang_test_tg/G.fst ERROR (fstisstochastic[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/G.fst

[ Stack-Trace: ] fstisstochastic(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4c3df4] fstisstochastic(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x43caad] fstisstochastic(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x454c4c] fstisstochastic(fst::ReadFstKaldiGeneric(std::cxx11::basic_string<char, std::char_traits, std::allocator >, bool)+0x71) [0x4478e2] fstisstochastic(main+0x227) [0x43b99d] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f6ad9b5c830] fstisstochastic(_start+0x29) [0x43b6a9]

kaldi::KaldiFatalErrorlocal/prepare_lm.sh: line 29: data/local/dict/lexicon.txt: No such file or directory ERROR: fstcompile: Open failed, file = tmpdir.g/select_empty.fst.txt ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: tmpdir.g/empty_words.fst Succeeded in formatting data. steps/make_mfcc.sh --nj 1 data/train_yesno exp/make_mfcc/train_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/train_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: Succeeded creating MFCC features for train_yesno steps/compute_cmvn_stats.sh data/train_yesno exp/make_mfcc/train_yesno mfcc Succeeded creating CMVN stats for train_yesno fix_data_dir.sh: kept all 31 utterances. fix_data_dir.sh: old files are kept in data/train_yesno/.backup steps/make_mfcc.sh --nj 1 data/test_yesno exp/make_mfcc/test_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/test_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (29 != 31); consider using utils/fix_data_dir.sh data/test_yesno steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error. steps/compute_cmvn_stats.sh data/test_yesno exp/make_mfcc/test_yesno mfcc Succeeded creating CMVN stats for test_yesno fix_data_dir.sh: kept 29 utterances out of 31 fix_data_dir.sh: old files are kept in data/test_yesno/.backup steps/train_mono.sh --nj 1 --cmd utils/run.pl --totgauss 400 data/train_yesno data/lang exp/mono0a cat: data/lang/oov.int: No such file or directory mkgraph.sh: expected data/lang_test_tg/L.fst to exist steps/decode.sh --nj 1 --cmd utils/run.pl exp/mono0a/graph_tgpr data/test_yesno exp/mono0a/decode_test_yesno steps/decode.sh: Error: no such file exp/mono0a/final.mdl grep: exp/mono0a/decode_testyesno/wer*: No such file or directory
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../thread/../thread/thread_operato
rs.cuh(115): error: calling a __device__ function("operator+") from a __host__ __device__ function("operator()") is not allowed
          detected during:
            instantiation of "T cub::Sum::operator()(const T &, const T &) const [with T=float2]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(143): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::ScanStep<HAS_IDENTITY,STEP,ScanOp>(T &, ScanOp, cub::Int2Type<STEP>) [with T=float2, 
LOGICAL_WARP_THREADS=32, PTX_ARCH=0, HAS_IDENTITY=false, STEP=0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(190): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, cub::Int2Type<IS_PRIMITIVE>) [with T=float2, LOGICAL_WA
RP_THREADS=32, PTX_ARCH=0, ScanOp=cub::Sum, IS_PRIMITIVE=0]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(229): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, Sc
anOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/specializations/warp_scan_smem.cuh(241): here
            instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=
0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war
p/warp_scan.cuh(503): here
            instantiation of "void cub::WarpScan<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, S
canOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/block_sca
n_raking.cuh(557): here
            instantiation of "void cub::BlockScanRaking<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, MEMOIZE, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK
_DIM_X=1024, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, MEMOIZE=false, PTX_ARCH=0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1766): her
e
            instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK_DIM
_X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0, ScanOp=cub::Sum]" 
/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1329): her
e
            instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveSum(T, T &, T &) [with T=float2, BLOCK_DIM_X=1024, 
ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0]" 
feature-online-cmvn-cuda.cu(65): here

i am getting the same error , have you solved the problem ? Thanks.

luitjens commented 5 years ago

Which toolkit are you using

On Fri, Nov 1, 2019 at 7:37 AM Esdsnqxz notifications@github.com wrote:

follow your instruction, i can make in src Success! but when run egs/yesno got this Error, make me confused. ()

Preparing train and test data cp: cannot stat '../../input/task.arpabo': No such file or directory cp: cannot stat 'input/lexicon_nosil.txt': No such file or directory cp: cannot stat 'input/lexicon.txt': No such file or directory cat: input/phones.txt: No such file or directory Dictionary preparation succeeded utils/prepare_lang.sh --position-dependent-phones false data/local/dict data/local/lang data/lang Checking data/local/dict/silence_phones.txt ... --> reading data/local/dict/silence_phones.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ... --> reading data/local/dict/optional_silence.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ... --> ERROR: data/local/dict/nonsilence_phones.txt is empty or not exists Error validating directory data/local/dict Here<<<<<<<<<<<<<<<< Preparing language models for test arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test_tg/words.txt input/task.arpabo data/lang_test_tg/G.fst ERROR (arpa2fst[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/words.txt

[ Stack-Trace: ] arpa2fst(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4b5e68] arpa2fst(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x434be5] arpa2fst(kaldi::Input::Input(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x44dc34] arpa2fst(main+0x5a1) [0x432ff7] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f9e237c9830] arpa2fst(_start+0x29) [0x432989]

kaldi::KaldiFatalErrorfstisstochastic data/lang_test_tg/G.fst ERROR (fstisstochastic[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/G.fst

[ Stack-Trace: ] fstisstochastic(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4c3df4] fstisstochastic(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x43caad] fstisstochastic(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x454c4c] fstisstochastic(fst::ReadFstKaldiGeneric(std::cxx11::basic_string<char, std::char_traits, std::allocator >, bool)+0x71) [0x4478e2] fstisstochastic(main+0x227) [0x43b99d] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f6ad9b5c830] fstisstochastic(_start+0x29) [0x43b6a9]

kaldi::KaldiFatalErrorlocal/prepare_lm.sh: line 29: data/local/dict/lexicon.txt: No such file or directory ERROR: fstcompile: Open failed, file = tmpdir.g/select_empty.fst.txt ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: tmpdir.g/empty_words.fst Succeeded in formatting data. steps/make_mfcc.sh --nj 1 data/train_yesno exp/make_mfcc/train_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/train_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: Succeeded creating MFCC features for train_yesno steps/compute_cmvn_stats.sh data/train_yesno exp/make_mfcc/train_yesno mfcc Succeeded creating CMVN stats for train_yesno fix_data_dir.sh: kept all 31 utterances. fix_data_dir.sh: old files are kept in data/train_yesno/.backup steps/make_mfcc.sh --nj 1 data/test_yesno exp/make_mfcc/test_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/test_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (29 != 31); consider using utils/fix_data_dir.sh data/test_yesno steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error. steps/compute_cmvn_stats.sh data/test_yesno exp/make_mfcc/test_yesno mfcc Succeeded creating CMVN stats for test_yesno fix_data_dir.sh: kept 29 utterances out of 31 fix_data_dir.sh: old files are kept in data/test_yesno/.backup steps/train_mono.sh --nj 1 --cmd utils/run.pl --totgauss 400 data/train_yesno data/lang exp/mono0a cat: data/lang/oov.int: No such file or directory mkgraph.sh: expected data/lang_test_tg/L.fst to exist steps/decode.sh --nj 1 --cmd utils/run.pl exp/mono0a/graph_tgpr data/test_yesno exp/mono0a/decode_test_yesno steps/decode.sh: Error: no such file exp/mono0a/final.mdl grep: exp/mono0a/decode_testyesno/wer*: No such file or directory

/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../thread/../thread/thread_operato rs.cuh(115): error: calling a device function("operator+") from a host device function("operator()") is not allowed detected during: instantiation of "T cub::Sum::operator()(const T &, const T &) const [with T=float2]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(143): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::ScanStep<HAS_IDENTITY,STEP,ScanOp>(T &, ScanOp, cub::Int2Type) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, HAS_IDENTITY=false, STEP=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(190): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, cub::Int2Type) [with T=float2, LOGICAL_WA RP_THREADS=32, PTX_ARCH=0, ScanOp=cub::Sum, IS_PRIMITIVE=0]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(229): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, Sc anOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(241): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH= 0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/warp_scan.cuh(503): here instantiation of "void cub::WarpScan<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, S canOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/block_sca n_raking.cuh(557): here instantiation of "void cub::BlockScanRaking<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, MEMOIZE, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK _DIM_X=1024, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, MEMOIZE=false, PTX_ARCH=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1766): her e instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK_DIM _X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1329): her e instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveSum(T, T &, T &) [with T=float2, BLOCK_DIM_X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0]" feature-online-cmvn-cuda.cu(65): here

i am getting the same error , have you solved the problem ? Thanks.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/3433?email_source=notifications&email_token=ABSFS4V32OGMOPL7MA7BLNTQRQWKNA5CNFSM4H4JXIB2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEC256KY#issuecomment-548790059, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSFS4R6QQWWB3D5VAB45HTQRQWKNANCNFSM4H4JXIBQ .

luitjens commented 4 years ago

After looking at this it seems like your code is picking up float2 operator+(...) from somewhere other than the one we have specified. Do you have the latest version of kaldi? Have you modified anything?

Can you verify line 29 is host device in your code?

https://github.com/kaldi-asr/kaldi/blob/master/src/cudafeat/feature-online-cmvn-cuda.cu

On Fri, Nov 1, 2019 at 10:05 AM Justin Luitjens luitjens@gmail.com wrote:

Which toolkit are you using

On Fri, Nov 1, 2019 at 7:37 AM Esdsnqxz notifications@github.com wrote:

follow your instruction, i can make in src Success! but when run egs/yesno got this Error, make me confused. ()

Preparing train and test data cp: cannot stat '../../input/task.arpabo': No such file or directory cp: cannot stat 'input/lexicon_nosil.txt': No such file or directory cp: cannot stat 'input/lexicon.txt': No such file or directory cat: input/phones.txt: No such file or directory Dictionary preparation succeeded utils/prepare_lang.sh --position-dependent-phones false data/local/dict data/local/lang data/lang Checking data/local/dict/silence_phones.txt ... --> reading data/local/dict/silence_phones.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ... --> reading data/local/dict/optional_silence.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ... --> ERROR: data/local/dict/nonsilence_phones.txt is empty or not exists Error validating directory data/local/dict Here<<<<<<<<<<<<<<<< Preparing language models for test arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test_tg/words.txt input/task.arpabo data/lang_test_tg/G.fst ERROR (arpa2fst[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/words.txt

[ Stack-Trace: ] arpa2fst(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4b5e68] arpa2fst(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x434be5] arpa2fst(kaldi::Input::Input(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x44dc34] arpa2fst(main+0x5a1) [0x432ff7] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f9e237c9830] arpa2fst(_start+0x29) [0x432989]

kaldi::KaldiFatalErrorfstisstochastic data/lang_test_tg/G.fst ERROR (fstisstochastic[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/G.fst

[ Stack-Trace: ] fstisstochastic(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4c3df4] fstisstochastic(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x43caad] fstisstochastic(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x454c4c] fstisstochastic(fst::ReadFstKaldiGeneric(std::cxx11::basic_string<char, std::char_traits, std::allocator >, bool)+0x71) [0x4478e2] fstisstochastic(main+0x227) [0x43b99d] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f6ad9b5c830] fstisstochastic(_start+0x29) [0x43b6a9]

kaldi::KaldiFatalErrorlocal/prepare_lm.sh: line 29: data/local/dict/lexicon.txt: No such file or directory ERROR: fstcompile: Open failed, file = tmpdir.g/select_empty.fst.txt ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: tmpdir.g/empty_words.fst Succeeded in formatting data. steps/make_mfcc.sh --nj 1 data/train_yesno exp/make_mfcc/train_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/train_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: Succeeded creating MFCC features for train_yesno steps/compute_cmvn_stats.sh data/train_yesno exp/make_mfcc/train_yesno mfcc Succeeded creating CMVN stats for train_yesno fix_data_dir.sh: kept all 31 utterances. fix_data_dir.sh: old files are kept in data/train_yesno/.backup steps/make_mfcc.sh --nj 1 data/test_yesno exp/make_mfcc/test_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/test_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (29 != 31); consider using utils/fix_data_dir.sh data/test_yesno steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error. steps/compute_cmvn_stats.sh data/test_yesno exp/make_mfcc/test_yesno mfcc Succeeded creating CMVN stats for test_yesno fix_data_dir.sh: kept 29 utterances out of 31 fix_data_dir.sh: old files are kept in data/test_yesno/.backup steps/train_mono.sh --nj 1 --cmd utils/run.pl --totgauss 400 data/train_yesno data/lang exp/mono0a cat: data/lang/oov.int: No such file or directory mkgraph.sh: expected data/lang_test_tg/L.fst to exist steps/decode.sh --nj 1 --cmd utils/run.pl exp/mono0a/graph_tgpr data/test_yesno exp/mono0a/decode_test_yesno steps/decode.sh: Error: no such file exp/mono0a/final.mdl grep: exp/mono0a/decode_testyesno/wer*: No such file or directory

/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../thread/../thread/thread_operato rs.cuh(115): error: calling a device function("operator+") from a host device function("operator()") is not allowed detected during: instantiation of "T cub::Sum::operator()(const T &, const T &) const [with T=float2]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(143): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::ScanStep<HAS_IDENTITY,STEP,ScanOp>(T &, ScanOp, cub::Int2Type) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, HAS_IDENTITY=false, STEP=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(190): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, cub::Int2Type) [with T=float2, LOGICAL_WA RP_THREADS=32, PTX_ARCH=0, ScanOp=cub::Sum, IS_PRIMITIVE=0]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(229): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, Sc anOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(241): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH= 0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/warp_scan.cuh(503): here instantiation of "void cub::WarpScan<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, S canOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/block_sca n_raking.cuh(557): here instantiation of "void cub::BlockScanRaking<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, MEMOIZE, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK _DIM_X=1024, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, MEMOIZE=false, PTX_ARCH=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1766): her e instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK_DIM _X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1329): her e instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveSum(T, T &, T &) [with T=float2, BLOCK_DIM_X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0]" feature-online-cmvn-cuda.cu(65): here

i am getting the same error , have you solved the problem ? Thanks.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/3433?email_source=notifications&email_token=ABSFS4V32OGMOPL7MA7BLNTQRQWKNA5CNFSM4H4JXIB2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEC256KY#issuecomment-548790059, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSFS4R6QQWWB3D5VAB45HTQRQWKNANCNFSM4H4JXIBQ .

luitjens commented 4 years ago

in fact i bet you are on an old version of the code because I fixed this a while ago:

https://github.com/kaldi-asr/kaldi/commit/9a380071609832d4e0b08bec1728fd9d9e5cc6f1#diff-28553e997b32cef544ccc4b872d51303

On Mon, Nov 4, 2019 at 11:44 AM Justin Luitjens luitjens@gmail.com wrote:

After looking at this it seems like your code is picking up float2 operator+(...) from somewhere other than the one we have specified. Do you have the latest version of kaldi? Have you modified anything?

Can you verify line 29 is host device in your code?

https://github.com/kaldi-asr/kaldi/blob/master/src/cudafeat/feature-online-cmvn-cuda.cu

On Fri, Nov 1, 2019 at 10:05 AM Justin Luitjens luitjens@gmail.com wrote:

Which toolkit are you using

On Fri, Nov 1, 2019 at 7:37 AM Esdsnqxz notifications@github.com wrote:

follow your instruction, i can make in src Success! but when run egs/yesno got this Error, make me confused. ()

Preparing train and test data cp: cannot stat '../../input/task.arpabo': No such file or directory cp: cannot stat 'input/lexicon_nosil.txt': No such file or directory cp: cannot stat 'input/lexicon.txt': No such file or directory cat: input/phones.txt: No such file or directory Dictionary preparation succeeded utils/prepare_lang.sh --position-dependent-phones false data/local/dict data/local/lang data/lang Checking data/local/dict/silence_phones.txt ... --> reading data/local/dict/silence_phones.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/silence_phones.txt is OK

Checking data/local/dict/optional_silence.txt ... --> reading data/local/dict/optional_silence.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/optional_silence.txt is OK

Checking data/local/dict/nonsilence_phones.txt ... --> ERROR: data/local/dict/nonsilence_phones.txt is empty or not exists Error validating directory data/local/dict Here<<<<<<<<<<<<<<<< Preparing language models for test arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test_tg/words.txt input/task.arpabo data/lang_test_tg/G.fst ERROR (arpa2fst[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/words.txt

[ Stack-Trace: ] arpa2fst(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4b5e68] arpa2fst(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x434be5] arpa2fst(kaldi::Input::Input(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x44dc34] arpa2fst(main+0x5a1) [0x432ff7] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f9e237c9830] arpa2fst(_start+0x29) [0x432989]

kaldi::KaldiFatalErrorfstisstochastic data/lang_test_tg/G.fst ERROR (fstisstochastic[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/G.fst

[ Stack-Trace: ] fstisstochastic(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4c3df4] fstisstochastic(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x43caad] fstisstochastic(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool*)+0xca) [0x454c4c] fstisstochastic(fst::ReadFstKaldiGeneric(std::cxx11::basic_string<char, std::char_traits, std::allocator >, bool)+0x71) [0x4478e2] fstisstochastic(main+0x227) [0x43b99d] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f6ad9b5c830] fstisstochastic(_start+0x29) [0x43b6a9]

kaldi::KaldiFatalErrorlocal/prepare_lm.sh: line 29: data/local/dict/lexicon.txt: No such file or directory ERROR: fstcompile: Open failed, file = tmpdir.g/select_empty.fst.txt ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: tmpdir.g/empty_words.fst Succeeded in formatting data. steps/make_mfcc.sh --nj 1 data/train_yesno exp/make_mfcc/train_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/train_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: Succeeded creating MFCC features for train_yesno steps/compute_cmvn_stats.sh data/train_yesno exp/make_mfcc/train_yesno mfcc Succeeded creating CMVN stats for train_yesno fix_data_dir.sh: kept all 31 utterances. fix_data_dir.sh: old files are kept in data/train_yesno/.backup steps/make_mfcc.sh --nj 1 data/test_yesno exp/make_mfcc/test_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/test_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (29 != 31); consider using utils/fix_data_dir.sh data/test_yesno steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error. steps/compute_cmvn_stats.sh data/test_yesno exp/make_mfcc/test_yesno mfcc Succeeded creating CMVN stats for test_yesno fix_data_dir.sh: kept 29 utterances out of 31 fix_data_dir.sh: old files are kept in data/test_yesno/.backup steps/train_mono.sh --nj 1 --cmd utils/run.pl --totgauss 400 data/train_yesno data/lang exp/mono0a cat: data/lang/oov.int: No such file or directory mkgraph.sh: expected data/lang_test_tg/L.fst to exist steps/decode.sh --nj 1 --cmd utils/run.pl exp/mono0a/graph_tgpr data/test_yesno exp/mono0a/decode_test_yesno steps/decode.sh: Error: no such file exp/mono0a/final.mdl grep: exp/mono0a/decode_testyesno/wer*: No such file or directory

/media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../thread/../thread/thread_operato rs.cuh(115): error: calling a device function("operator+") from a host device function("operator()") is not allowed detected during: instantiation of "T cub::Sum::operator()(const T &, const T &) const [with T=float2]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(143): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::ScanStep<HAS_IDENTITY,STEP,ScanOp>(T &, ScanOp, cub::Int2Type) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, HAS_IDENTITY=false, STEP=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(190): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, cub::Int2Type) [with T=float2, LOGICAL_WA RP_THREADS=32, PTX_ARCH=0, ScanOp=cub::Sum, IS_PRIMITIVE=0]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(229): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, Sc anOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/specializations/warp_scan_smem.cuh(241): here instantiation of "void cub::WarpScanSmem<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH= 0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/../../war p/warp_scan.cuh(503): here instantiation of "void cub::WarpScan<T, LOGICAL_WARP_THREADS, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, LOGICAL_WARP_THREADS=32, PTX_ARCH=0, S canOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/specializations/block_sca n_raking.cuh(557): here instantiation of "void cub::BlockScanRaking<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, MEMOIZE, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK _DIM_X=1024, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, MEMOIZE=false, PTX_ARCH=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1766): her e instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveScan(T, T &, ScanOp, T &) [with T=float2, BLOCK_DIM _X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0, ScanOp=cub::Sum]" /media/shipley/d14784b3-14f6-4ea0-89f2-ccc4c5d28966/voice_learn_material/kaldi-master/tools/cub-1.8.0/cub/block/specializations/../../block/../block/block_scan.cuh(1329): her e instantiation of "void cub::BlockScan<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, PTX_ARCH>::InclusiveSum(T, T &, T &) [with T=float2, BLOCK_DIM_X=1024, ALGORITHM=cub::BLOCK_SCAN_RAKING, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, PTX_ARCH=0]" feature-online-cmvn-cuda.cu(65): here

i am getting the same error , have you solved the problem ? Thanks.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/3433?email_source=notifications&email_token=ABSFS4V32OGMOPL7MA7BLNTQRQWKNA5CNFSM4H4JXIB2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEC256KY#issuecomment-548790059, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSFS4R6QQWWB3D5VAB45HTQRQWKNANCNFSM4H4JXIBQ .

danpovey commented 4 years ago

need to update your Kaldi codebase

On Fri, Aug 21, 2020 at 10:22 AM 唐宝 notifications@github.com wrote:

I am getting a similar error. When computing MFCC features. I get a similiar error to the one you commented.

`# paste-feats --length-tolerance=2 "ark:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |" " ark,s,cs:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats -- verbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- |" ark:- | copy-feats --compress=true --write-num-frames=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfc c/log/utt2num_frames.1 ark:- ark,scp:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1.ark,/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1. scp

paste-feats --length-tolerance=2 'ark:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |' 'ar k,s,cs:extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats --ve rbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- |' ark:- copy-feats --compress=true --write-num-frames=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2num_frames.1 ark:- ark,scp:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw

_mfcc_pitch_mfcc.1.ark,/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/data/raw_mfcc_pitch_mfcc.1.scp extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:-

Create MFCC feature files. Usage: compute-mfcc-feats [options...]

Options: --allow-downsample : If true, allow the input waveform to have a higher frequency than the specified --sample-frequency (and we'll downsample). (bool, default = false) --blackman-coeff : Constant coefficient for generalized Blackman window. (float, default = 0.42) ......................... ......................... ......................... Standard options: --config : Configuration file to read (this option may be repeated) (string, default = "") --help : Print out usage message (bool, default = false) --print-args : Print the command line arguments (to stderr) (bool, default = true) --verbose : Verbose level (higher->more logging) (int, default = 0)

Command line was: compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ar k:- ERROR (compute-mfcc-feats[5.5.93~1418-faa1f]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const) kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::ParseOptions::Read(int, char const const*) main __libc_start_main compute-mfcc-feats() [0x433d89]

ERROR (compute-mfcc-feats[5.5.93~1418-faa1f]:Read():parse-options.cc:372) Invalid option --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const) kaldi::MessageLogger::~MessageLogger() kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::ParseOptions::Read(int, char const const*) main __libc_start_main compute-mfcc-feats() [0x433d89]

extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- process-kaldi-pitch-feats ark:- ark:- compute-kaldi-pitch-feats --verbose=2 --config=conf/pitch.conf ark:- ark:- LOG (extract-segments[5.5.931418-faa1f]:main():extract-segments.cc:193) Successfully processed 3 lines out of 3 in the segments file. WARNING (paste-feats[5.5.931418-faa1f]:Close():kaldi-io.cc:515) Pipe extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train /mfcc/log/segments.1 ark:- | compute-kaldi-pitch-feats --verbose=2 --config=conf/pitch.conf ark:- ark:- | process-kaldi-pitch-feats ark:- ark:- | had nonzero return status 36096 LOG (paste-feats[5.5.931418-faa1f]:main():paste-feats.cc:158) Done 0 utts, errors on 0 WARNING (paste-feats[5.5.931418-faa1f]:Close():kaldi-io.cc:515) Pipe extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train /mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/c onf/mfcc.conf ark:- ark:- | had nonzero return status 65280 ERROR (paste-feats[5.5.93~1418-faa1f]:~SequentialTableReaderArchiveImpl():util/kaldi-table-inl.h:678) TableReader: error detected closing archive 'extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data- benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/l og/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |'

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*) kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix

::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix ::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReader<kaldi::KaldiObjectHolder ::~SequentialTableReader() main __libc_start_main paste-feats() [0x42ddd9]

ERROR (paste-feats[5.5.93~1418-faa1f]:~SequentialTableReaderArchiveImpl():util/kaldi-table-inl.h:678) TableReader: error detected closing archive 'extract-segments scp,p:/home/b.bors/speech-asr/egs/spanish/data- benet/train/mfcc/wav.scp /home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/log/segments.1 ark:- | compute-mfcc-feats --write-utt2dur=ark,t:/home/b.bors/speech-asr/egs/spanish/data-benet/train/mfcc/l og/utt2dur.1 --verbose=2 --config=/home/b.bors/speech-asr/egs/spanish/conf/mfcc.conf ark:- ark:- |'

[ Stack-Trace: ] kaldi::MessageLogger::HandleMessage(kaldi::LogMessageEnvelope const&, char const*) kaldi::MessageLogger::~MessageLogger() kaldi::FatalMessageLogger::~FatalMessageLogger() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix

::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReaderArchiveImpl<kaldi::KaldiObjectHolder<kaldi::Matrix ::~SequentialTableReaderArchiveImpl() kaldi::SequentialTableReader<kaldi::KaldiObjectHolder ::~SequentialTableReader() main __libc_start_main paste-feats() [0x42ddd9]

terminate called after throwing an instance of 'std::runtime_error' what(): LOG (copy-feats[5.5.93~1418-faa1f]:main():copy-feats.cc:143) Copied 0 feature matrices.

Accounting: time=1 threads=1 # Ended (code 1) at Mon Jul 8 10:29:43

CEST 2019, elapsed time 1 seconds

I suspect you changed the repository somehow. That file ../../input/task.arpabo is part of the repo. Do "git status" at top level to see what you changed or deleted. … <#m4183276752685068276> On Wed, Jul 3, 2019 at 9:49 PM shipleyxie @.> wrote: follow your instruction, i can make in src Success! but when run egs/yesno got this Error, make me confused. () ------------------------------ Preparing train and test data cp: cannot stat '../../input/task.arpabo': No such file or directory cp: cannot stat 'input/lexicon_nosil.txt': No such file or directory cp: cannot stat 'input/lexicon.txt': No such file or directory cat: input/phones.txt: No such file or directory Dictionary preparation succeeded utils/prepare_lang.sh --position-dependent-phones false data/local/dict data/local/lang data/lang Checking data/local/dict/silence_phones.txt ... --> reading data/local/dict/silence_phones.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/silence_phones.txt is OK Checking data/local/dict/optional_silence.txt ... --> reading data/local/dict/optional_silence.txt --> text seems to be UTF-8 or ASCII, checking whitespaces --> text contains only allowed whitespaces --> data/local/dict/optional_silence.txt is OK Checking data/local/dict/nonsilence_phones.txt ... --> ERROR: data/local/dict/nonsilence_phones.txt is empty or not exists Error validating directory data/local/dict Here<<<<<<<<<<<<<<<< Preparing language models for test arpa2fst --disambig-symbol=#0 --read-symbol-table=data/lang_test_tg/words.txt input/task.arpabo data/lang_test_tg/G.fst ERROR (arpa2fst[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/words.txt [ Stack-Trace: ] arpa2fst(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4b5e68] arpa2fst(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x434be5] arpa2fst(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool)+0xca) [0x44dc34] arpa2fst(main+0x5a1) [0x432ff7] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f9e237c9830] arpa2fst(_start+0x29) [0x432989] kaldi::KaldiFatalErrorfstisstochastic data/lang_test_tg/G.fst ERROR (fstisstochastic[5.5]:Input():kaldi-io.cc:756) Error opening input stream data/lang_test_tg/G.fst [ Stack-Trace: ] fstisstochastic(kaldi::MessageLogger::LogMessage() const+0x82c) [0x4c3df4] fstisstochastic(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x43caad] fstisstochastic(kaldi::Input::Input(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&, bool)+0xca) [0x454c4c] fstisstochastic(fst::ReadFstKaldiGeneric(std::__cxx11::basic_string<char, std::char_traits, std::allocator >, bool)+0x71) [0x4478e2] fstisstochastic(main+0x227) [0x43b99d] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0) [0x7f6ad9b5c830] fstisstochastic(start+0x29) [0x43b6a9] kaldi::KaldiFatalErrorlocal/prepare_lm.sh: line 29: data/local/dict/lexicon.txt: No such file or directory ERROR: fstcompile: Open failed, file = tmpdir.g/select_empty.fst.txt ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: standard input ERROR: FstHeader::Read: Bad FST header: tmpdir.g/empty_words.fst Succeeded in formatting data. steps/make_mfcc.sh --nj 1 data/train_yesno exp/make_mfcc/train_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/train_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: Succeeded creating MFCC features for train_yesno steps/compute_cmvn_stats.sh data/train_yesno exp/make_mfcc/train_yesno mfcc Succeeded creating CMVN stats for train_yesno fix_data_dir.sh: kept all 31 utterances. fix_data_dir.sh: old files are kept in data/train_yesno/.backup steps/make_mfcc.sh --nj 1 data/test_yesno exp/make_mfcc/test_yesno mfcc utils/validate_data_dir.sh: WARNING: you have only one speaker. This probably a bad idea. Search for the word 'bold' in http://kaldi-asr.org/doc/data_prep.html http://kaldi-asr.org/doc/data_prep.html for more information. utils/validate_data_dir.sh: Successfully validated data-directory data/test_yesno steps/make_mfcc.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance. steps/make_mfcc.sh: It seems not all of the feature files were successfully procesed (29 != 31); consider using utils/fix_data_dir.sh data/test_yesno steps/make_mfcc.sh: Less than 95% the features were successfully generated. Probably a serious error. steps/compute_cmvn_stats.sh data/test_yesno exp/make_mfcc/test_yesno mfcc Succeeded creating CMVN stats for test_yesno fix_data_dir.sh: kept 29 utterances out of 31 fix_data_dir.sh: old files are kept in data/test_yesno/.backup steps/train_mono.sh --nj 1 --cmd utils/run.pl http://run.pl --totgauss 400 data/train_yesno data/lang exp/mono0a cat: data/lang/oov.int http://oov.int: No such file or directory mkgraph.sh: expected data/lang_test_tg/L.fst to exist steps/decode.sh --nj 1 --cmd utils/run.pl http://run.pl exp/mono0a/graph_tgpr data/test_yesno exp/mono0a/decode_test_yesno steps/decode.sh: Error: no such file exp/mono0a/final.mdl grep: exp/mono0a/decode_test_yesno/wer: No such file or directory ------------------------------ — You are receiving this because you commented. Reply to this email directly, view it on GitHub <

3433 https://github.com/kaldi-asr/kaldi/issues/3433?email_source=notifications&email_token=AAZFLOYPPRAWGO5QXALF6VLP5VJLRA5CNFSM4H4JXIB2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZGCYII#issuecomment-508308513>,

or mute the thread https://github.com/notifications/unsubscribe-auth/AAZFLO5XAZTEOL3X4JWYQRDP5VJLRANCNFSM4H4JXIBQ .

hi, I meet the issue that is the same as your, but i cant find how to solve it, so i want to kown what you do for it， thank for you, (i am sorry for my enlish if i may be offend you in my expression, thank you very much)

— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/3433#issuecomment-678001212, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAZFLO5IQMEYENXDZFGWAPTSBXK73ANCNFSM4H4JXIBQ .