API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Sep 11th, 2016
296
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 13.03 KB | None | 0 0
raw download clone embed print report
  1. kidi@kidi-ThinkPad-T420s:~/kaldi-trunk/egs/setup_base_files$ ./workspace_setup.sh "start" /home/kidi/kaldi-trunk/egs/setup_base_files/database/an4/data/ /home/kidi/kaldi-trunk/egs/setup_base_files/database/an4/utterance/transcript
  2. Data TRAIN/TEST SPLITTED
  3. UTT/wav.scp/utt2spk created for train and test!
  4. Text and utt2spk sorted
  5. wav.scp sorted
  6. spk2utt created!
  7. --2016-09-11 18:40:18-- http://svn.code.sf.net/p/cmusphinx/code/trunk/cmudict/sphinxdict/cmudict.0.7a_SPHINX_40
  8. Resolving svn.code.sf.net (svn.code.sf.net)... 216.34.181.157
  9. Connecting to svn.code.sf.net (svn.code.sf.net)|216.34.181.157|:80... connected.
  10. HTTP request sent, awaiting response... 200 OK
  11. Length: 3231422 (3.1M) [text/plain]
  12. Saving to: ‘lexicon.txt’
  13.  
  14. 100%[======================================>] 3,231,422 975KB/s in 3.2s
  15.  
  16. 2016-09-11 18:40:22 (975 KB/s) - ‘lexicon.txt’ saved [3231422/3231422]
  17.  
  18. Filtered lexicon!
  19. Checking data/local/lang/silence_phones.txt ...
  20. --> reading data/local/lang/silence_phones.txt
  21. --> data/local/lang/silence_phones.txt is OK
  22.  
  23. Checking data/local/lang/optional_silence.txt ...
  24. --> reading data/local/lang/optional_silence.txt
  25. --> data/local/lang/optional_silence.txt is OK
  26.  
  27. Checking data/local/lang/nonsilence_phones.txt ...
  28. --> reading data/local/lang/nonsilence_phones.txt
  29. --> data/local/lang/nonsilence_phones.txt is OK
  30.  
  31. Checking disjoint: silence_phones.txt, nonsilence_phones.txt
  32. --> disjoint property is OK.
  33.  
  34. Checking data/local/lang/lexicon.txt
  35. --> reading data/local/lang/lexicon.txt
  36. --> data/local/lang/lexicon.txt is OK
  37.  
  38. Checking data/local/lang/extra_questions.txt ...
  39. --> data/local/lang/extra_questions.txt is empty (this is OK)
  40. --> SUCCESS [validating dictionary directory data/local/lang]
  41.  
  42. **Creating data/local/lang/lexiconp.txt from data/local/lang/lexicon.txt
  43. fstaddselfloops data/lang/phones/wdisambig_phones.int data/lang/phones/wdisambig_words.int
  44. prepare_lang.sh: validating output directory
  45. utils/validate_lang.pl data/lang
  46. Checking data/lang/phones.txt ...
  47. --> data/lang/phones.txt is OK
  48.  
  49. Checking words.txt: #0 ...
  50. --> data/lang/words.txt is OK
  51.  
  52. Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
  53. --> silence.txt and nonsilence.txt are disjoint
  54. --> silence.txt and disambig.txt are disjoint
  55. --> disambig.txt and nonsilence.txt are disjoint
  56. --> disjoint property is OK
  57.  
  58. Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
  59. --> summation property is OK
  60.  
  61. Checking data/lang/phones/context_indep.{txt, int, csl} ...
  62. --> 5 entry/entries in data/lang/phones/context_indep.txt
  63. --> data/lang/phones/context_indep.int corresponds to data/lang/phones/context_indep.txt
  64. --> data/lang/phones/context_indep.csl corresponds to data/lang/phones/context_indep.txt
  65. --> data/lang/phones/context_indep.{txt, int, csl} are OK
  66.  
  67. Checking data/lang/phones/nonsilence.{txt, int, csl} ...
  68. --> 136 entry/entries in data/lang/phones/nonsilence.txt
  69. --> data/lang/phones/nonsilence.int corresponds to data/lang/phones/nonsilence.txt
  70. --> data/lang/phones/nonsilence.csl corresponds to data/lang/phones/nonsilence.txt
  71. --> data/lang/phones/nonsilence.{txt, int, csl} are OK
  72.  
  73. Checking data/lang/phones/silence.{txt, int, csl} ...
  74. --> 5 entry/entries in data/lang/phones/silence.txt
  75. --> data/lang/phones/silence.int corresponds to data/lang/phones/silence.txt
  76. --> data/lang/phones/silence.csl corresponds to data/lang/phones/silence.txt
  77. --> data/lang/phones/silence.{txt, int, csl} are OK
  78.  
  79. Checking data/lang/phones/optional_silence.{txt, int, csl} ...
  80. --> 1 entry/entries in data/lang/phones/optional_silence.txt
  81. --> data/lang/phones/optional_silence.int corresponds to data/lang/phones/optional_silence.txt
  82. --> data/lang/phones/optional_silence.csl corresponds to data/lang/phones/optional_silence.txt
  83. --> data/lang/phones/optional_silence.{txt, int, csl} are OK
  84.  
  85. Checking data/lang/phones/disambig.{txt, int, csl} ...
  86. --> 4 entry/entries in data/lang/phones/disambig.txt
  87. --> data/lang/phones/disambig.int corresponds to data/lang/phones/disambig.txt
  88. --> data/lang/phones/disambig.csl corresponds to data/lang/phones/disambig.txt
  89. --> data/lang/phones/disambig.{txt, int, csl} are OK
  90.  
  91. Checking data/lang/phones/roots.{txt, int} ...
  92. --> 35 entry/entries in data/lang/phones/roots.txt
  93. --> data/lang/phones/roots.int corresponds to data/lang/phones/roots.txt
  94. --> data/lang/phones/roots.{txt, int} are OK
  95.  
  96. Checking data/lang/phones/sets.{txt, int} ...
  97. --> 35 entry/entries in data/lang/phones/sets.txt
  98. --> data/lang/phones/sets.int corresponds to data/lang/phones/sets.txt
  99. --> data/lang/phones/sets.{txt, int} are OK
  100.  
  101. Checking data/lang/phones/extra_questions.{txt, int} ...
  102. --> 9 entry/entries in data/lang/phones/extra_questions.txt
  103. --> data/lang/phones/extra_questions.int corresponds to data/lang/phones/extra_questions.txt
  104. --> data/lang/phones/extra_questions.{txt, int} are OK
  105.  
  106. Checking data/lang/phones/word_boundary.{txt, int} ...
  107. --> 141 entry/entries in data/lang/phones/word_boundary.txt
  108. --> data/lang/phones/word_boundary.int corresponds to data/lang/phones/word_boundary.txt
  109. --> data/lang/phones/word_boundary.{txt, int} are OK
  110.  
  111. Checking optional_silence.txt ...
  112. --> reading data/lang/phones/optional_silence.txt
  113. --> data/lang/phones/optional_silence.txt is OK
  114.  
  115. Checking disambiguation symbols: #0 and #1
  116. --> data/lang/phones/disambig.txt has "#0" and "#1"
  117. --> data/lang/phones/disambig.txt is OK
  118.  
  119. Checking topo ...
  120.  
  121. Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
  122. --> data/lang/phones/word_boundary.txt doesn't include disambiguation symbols
  123. --> data/lang/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
  124. --> data/lang/phones/word_boundary.txt is OK
  125.  
  126. Checking word-level disambiguation symbols...
  127. --> data/lang/phones/wdisambig.txt exists (newer prepare_lang.sh)
  128. Checking word_boundary.int and disambig.int
  129. --> generating a 73 word sequence
  130. --> resulting phone sequence from L.fst corresponds to the word sequence
  131. --> L.fst is OK
  132. --> generating a 88 word sequence
  133. --> resulting phone sequence from L_disambig.fst corresponds to the word sequence
  134. --> L_disambig.fst is OK
  135.  
  136. Checking data/lang/oov.{txt, int} ...
  137. --> 1 entry/entries in data/lang/oov.txt
  138. --> data/lang/oov.int corresponds to data/lang/oov.txt
  139. --> data/lang/oov.{txt, int} are OK
  140.  
  141. --> data/lang/L.fst is olabel sorted
  142. --> data/lang/L_disambig.fst is olabel sorted
  143. --> SUCCESS [validating lang directory data/lang]
  144. utils/validate_data_dir.sh: Successfully validated data-directory data/train
  145. Lexicon and phones generated! - Run train scripts.
  146. kidi@kidi-ThinkPad-T420s:~/kaldi-trunk/egs/setup_base_files$ rm -rf ../start/
  147. kidi@kidi-ThinkPad-T420s:~/kaldi-trunk/egs/setup_base_files$ ./workspace_setup.sh "start" /home/kidi/kaldi-trunk/egs/setup_base_files/database/an4/data/ /home/kidi/kaldi-trunk/egs/setup_base_files/database/an4/utterance/transcript
  148. Data TRAIN/TEST SPLITTED
  149. UTT/wav.scp/utt2spk created for train and test!
  150. Text and utt2spk sorted
  151. wav.scp sorted
  152. spk2utt created!
  153. --2016-09-11 18:40:43-- http://svn.code.sf.net/p/cmusphinx/code/trunk/cmudict/sphinxdict/cmudict.0.7a_SPHINX_40
  154. Resolving svn.code.sf.net (svn.code.sf.net)... 216.34.181.157
  155. Connecting to svn.code.sf.net (svn.code.sf.net)|216.34.181.157|:80... connected.
  156. HTTP request sent, awaiting response... 200 OK
  157. Length: 3231422 (3.1M) [text/plain]
  158. Saving to: ‘lexicon.txt’
  159.  
  160. 100%[======================================>] 3,231,422 1.08MB/s in 2.8s
  161.  
  162. 2016-09-11 18:40:46 (1.08 MB/s) - ‘lexicon.txt’ saved [3231422/3231422]
  163.  
  164. Filtered lexicon!
  165. Checking data/local/lang/silence_phones.txt ...
  166. --> reading data/local/lang/silence_phones.txt
  167. --> data/local/lang/silence_phones.txt is OK
  168.  
  169. Checking data/local/lang/optional_silence.txt ...
  170. --> reading data/local/lang/optional_silence.txt
  171. --> data/local/lang/optional_silence.txt is OK
  172.  
  173. Checking data/local/lang/nonsilence_phones.txt ...
  174. --> reading data/local/lang/nonsilence_phones.txt
  175. --> data/local/lang/nonsilence_phones.txt is OK
  176.  
  177. Checking disjoint: silence_phones.txt, nonsilence_phones.txt
  178. --> disjoint property is OK.
  179.  
  180. Checking data/local/lang/lexicon.txt
  181. --> reading data/local/lang/lexicon.txt
  182. --> data/local/lang/lexicon.txt is OK
  183.  
  184. Checking data/local/lang/extra_questions.txt ...
  185. --> data/local/lang/extra_questions.txt is empty (this is OK)
  186. --> SUCCESS [validating dictionary directory data/local/lang]
  187.  
  188. **Creating data/local/lang/lexiconp.txt from data/local/lang/lexicon.txt
  189. fstaddselfloops data/lang/phones/wdisambig_phones.int data/lang/phones/wdisambig_words.int
  190. prepare_lang.sh: validating output directory
  191. utils/validate_lang.pl data/lang
  192. Checking data/lang/phones.txt ...
  193. --> data/lang/phones.txt is OK
  194.  
  195. Checking words.txt: #0 ...
  196. --> data/lang/words.txt is OK
  197.  
  198. Checking disjoint: silence.txt, nonsilence.txt, disambig.txt ...
  199. --> silence.txt and nonsilence.txt are disjoint
  200. --> silence.txt and disambig.txt are disjoint
  201. --> disambig.txt and nonsilence.txt are disjoint
  202. --> disjoint property is OK
  203.  
  204. Checking sumation: silence.txt, nonsilence.txt, disambig.txt ...
  205. --> summation property is OK
  206.  
  207. Checking data/lang/phones/context_indep.{txt, int, csl} ...
  208. --> 5 entry/entries in data/lang/phones/context_indep.txt
  209. --> data/lang/phones/context_indep.int corresponds to data/lang/phones/context_indep.txt
  210. --> data/lang/phones/context_indep.csl corresponds to data/lang/phones/context_indep.txt
  211. --> data/lang/phones/context_indep.{txt, int, csl} are OK
  212.  
  213. Checking data/lang/phones/nonsilence.{txt, int, csl} ...
  214. --> 136 entry/entries in data/lang/phones/nonsilence.txt
  215. --> data/lang/phones/nonsilence.int corresponds to data/lang/phones/nonsilence.txt
  216. --> data/lang/phones/nonsilence.csl corresponds to data/lang/phones/nonsilence.txt
  217. --> data/lang/phones/nonsilence.{txt, int, csl} are OK
  218.  
  219. Checking data/lang/phones/silence.{txt, int, csl} ...
  220. --> 5 entry/entries in data/lang/phones/silence.txt
  221. --> data/lang/phones/silence.int corresponds to data/lang/phones/silence.txt
  222. --> data/lang/phones/silence.csl corresponds to data/lang/phones/silence.txt
  223. --> data/lang/phones/silence.{txt, int, csl} are OK
  224.  
  225. Checking data/lang/phones/optional_silence.{txt, int, csl} ...
  226. --> 1 entry/entries in data/lang/phones/optional_silence.txt
  227. --> data/lang/phones/optional_silence.int corresponds to data/lang/phones/optional_silence.txt
  228. --> data/lang/phones/optional_silence.csl corresponds to data/lang/phones/optional_silence.txt
  229. --> data/lang/phones/optional_silence.{txt, int, csl} are OK
  230.  
  231. Checking data/lang/phones/disambig.{txt, int, csl} ...
  232. --> 4 entry/entries in data/lang/phones/disambig.txt
  233. --> data/lang/phones/disambig.int corresponds to data/lang/phones/disambig.txt
  234. --> data/lang/phones/disambig.csl corresponds to data/lang/phones/disambig.txt
  235. --> data/lang/phones/disambig.{txt, int, csl} are OK
  236.  
  237. Checking data/lang/phones/roots.{txt, int} ...
  238. --> 35 entry/entries in data/lang/phones/roots.txt
  239. --> data/lang/phones/roots.int corresponds to data/lang/phones/roots.txt
  240. --> data/lang/phones/roots.{txt, int} are OK
  241.  
  242. Checking data/lang/phones/sets.{txt, int} ...
  243. --> 35 entry/entries in data/lang/phones/sets.txt
  244. --> data/lang/phones/sets.int corresponds to data/lang/phones/sets.txt
  245. --> data/lang/phones/sets.{txt, int} are OK
  246.  
  247. Checking data/lang/phones/extra_questions.{txt, int} ...
  248. --> 9 entry/entries in data/lang/phones/extra_questions.txt
  249. --> data/lang/phones/extra_questions.int corresponds to data/lang/phones/extra_questions.txt
  250. --> data/lang/phones/extra_questions.{txt, int} are OK
  251.  
  252. Checking data/lang/phones/word_boundary.{txt, int} ...
  253. --> 141 entry/entries in data/lang/phones/word_boundary.txt
  254. --> data/lang/phones/word_boundary.int corresponds to data/lang/phones/word_boundary.txt
  255. --> data/lang/phones/word_boundary.{txt, int} are OK
  256.  
  257. Checking optional_silence.txt ...
  258. --> reading data/lang/phones/optional_silence.txt
  259. --> data/lang/phones/optional_silence.txt is OK
  260.  
  261. Checking disambiguation symbols: #0 and #1
  262. --> data/lang/phones/disambig.txt has "#0" and "#1"
  263. --> data/lang/phones/disambig.txt is OK
  264.  
  265. Checking topo ...
  266.  
  267. Checking word_boundary.txt: silence.txt, nonsilence.txt, disambig.txt ...
  268. --> data/lang/phones/word_boundary.txt doesn't include disambiguation symbols
  269. --> data/lang/phones/word_boundary.txt is the union of nonsilence.txt and silence.txt
  270. --> data/lang/phones/word_boundary.txt is OK
  271.  
  272. Checking word-level disambiguation symbols...
  273. --> data/lang/phones/wdisambig.txt exists (newer prepare_lang.sh)
  274. Checking word_boundary.int and disambig.int
  275. --> generating a 71 word sequence
  276. --> resulting phone sequence from L.fst corresponds to the word sequence
  277. --> L.fst is OK
  278. --> generating a 96 word sequence
  279. --> resulting phone sequence from L_disambig.fst corresponds to the word sequence
  280. --> L_disambig.fst is OK
  281.  
  282. Checking data/lang/oov.{txt, int} ...
  283. --> 1 entry/entries in data/lang/oov.txt
  284. --> data/lang/oov.int corresponds to data/lang/oov.txt
  285. --> data/lang/oov.{txt, int} are OK
  286.  
  287. --> data/lang/L.fst is olabel sorted
  288. --> data/lang/L_disambig.fst is olabel sorted
  289. --> SUCCESS [validating lang directory data/lang]
  290. utils/validate_data_dir.sh: file data/train/utt2spk is not in sorted order or has duplicates
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!