search

MontrealCorpusTools / Montreal-Forced-Aligner

Command line utility for forced alignment using Kaldi
https://montrealcorpustools.github.io/Montreal-Forced-Aligner/
MIT License
1.29k stars 242 forks source link

[BUG] g2p FST error #644

Open lifeiteng opened 1 year ago

lifeiteng commented 1 year ago

Debugging checklist

Describe the issue A clear and concise description of what the bug is.

mfa server start
mfa g2p -j 8 --clean oovs_sed.txt english_us_arpa g2pped_oovs.txt --dictionary_path english_us_arpa

2023-05-31 17:14:12,659 INFO [generator.py:514] Generating pronunciations...
2023-05-31 17:14:12,922 DEBUG [generator.py:551] Skipping 0 words for containing the following graphemes:
   0% ________________________________________________________________________________________________________________________________________________________________________________________________________________________________________ 284/184,072  [ 0:02:50 < 36:25:53 , 1 it/s ]
LEVEL(FST_FLAGS_fst_error_fatal ? base_logging::FATAL : base_logging::ERROR): StringWeight::Plus: Unequal arguments (non-functional FST?) w1 = 64 w2 = 134217792
   0% ________________________________________________________________________________________________________________________________________________________________________________________________________________________________________ 284/184,072  [ 0:02:52 < 36:25:53 , 1 it/s ]
LEVEL(FST_FLAGS_fst_error_fatal ? base_logging::FATAL : base_logging::ERROR): StringWeight::Plus: Unequal arguments (non-functional FST?) w1 = 61 w2 = 134217789
   0% ________________________________________________________________________________________________________________________________________________________________________________________________________________________________________ 284/184,072  [ 0:02:52 < 36:25:53 , 1 it/s ]
LEVEL(FST_FLAGS_fst_error_fatal ? base_logging::FATAL : base_logging::ERROR): StringWeight::Plus: Unequal arguments (non-functional FST?) w1 = 61 w2 = 134217789
   0% ____________________________________________________________________________________________________________________________________________________________

oovs_sed.txt oovs_sed.txt

lifeiteng commented 1 year ago

try using mfa g2p my_corpus_dir same errors

mfa server start
mfa g2p -j4 --clean ${sub_data_dir} english_us_arpa ${sub_data_dir}/g2pped_oovs.txt --dictionary_path english_us_arpa

   6% ______________________________________________________________________________________________________________________________________________________________________________________________________ 460/7,547  [ 0:03:53 < 0:34:57 , 3 it/s ]
LEVEL(FST_FLAGS_fst_error_fatal ? base_logging::FATAL : base_logging::ERROR): StringWeight::Plus: Unequal arguments (non-functional FST?) w1 = 41 w2 = 134217769
LEVEL(FST_FLAGS_fst_error_fatal ? base_logging::FATAL : base_logging::ERROR): StringWeight::Plus: Unequal arguments (non-functional FST?) w1 = 42 w2 = 134217770
   6% ______________________________________________________________________________________________________________________________________________________________________________________________________ 460/7,547  [ 0:03:54 < 0:34:57 , 3 it/s ]
LEVEL(FST_FLAGS_fst_error_fatal ? base_logging::FATAL : base_logging::ERROR): StringWeight::Plus: Unequal arguments (non-functional FST?) w1 = 41 w2 = 134217769
LEVEL(FST_FLAGS_fst_error_fatal ? base_logging::FATAL : base_logging::ERROR): StringWeight::Plus: Unequal arguments (non-functional FST?) w1 = 42 w2 = 134217770