38 lines
3.5 KiB
Plaintext
38 lines
3.5 KiB
Plaintext
|
File(3) - Wrapper for stdio streams
|
||
|
|
LM(3) - Generic language model
|
||
|
|
Prob(3) - Probabilities for SRILM
|
||
|
|
TEMPLATE(1), XXX(1) - XXX
|
||
|
|
TEMPLATE(3), XXX(3) - XXX
|
||
|
|
TEMPLATE(5), XXX(5) - XXX
|
||
|
|
TEMPLATE(7), XXX(7) - XXX
|
||
|
|
Vocab(3) - Vocabulary indexing for SRILM
|
||
|
|
anti-ngram(1) - count posterior-weighted N-grams in N-best lists
|
||
|
|
classes-format(5) - File format for word class definitions
|
||
|
|
disambig(1) - disambiguate text tokens using an N-gram model
|
||
|
|
hidden-ngram(1) - tag hidden events between words
|
||
|
|
lattice-tool(1) - manipulate word lattices
|
||
|
|
lm-scripts(1), add-dummy-bows(1), change-lm-vocab(1), empty-sentence-lm(1), get-unigram-probs(1), make-hiddens-lm(1), make-lm-subset(1), make-sub-lm(1), remove-lowprob-ngrams(1), reverse-lm(1), sort-lm(1) - manipulate N-gram language models
|
||
|
|
metadb(1) - retrieve configuration information
|
||
|
|
multi-ngram(1) - build multiword N-gram models
|
||
|
|
nbest-format(5) - File formats for N-best hypotheses lists
|
||
|
|
nbest-lattice(1) - rescore N-best lists and lattices
|
||
|
|
nbest-mix(1) - interpolate N-best posterior probabilities
|
||
|
|
nbest-optimize(1) - optimize score combination for N-best word error minimization
|
||
|
|
nbest-pron-score(1) - score pronunciations and pauses in N-best hypotheses
|
||
|
|
nbest-scripts(1), combine-rover-controls(1), compare-sclite(1), compute-sclite(1), fix-ctm(1), merge-nbest(1), nbest-error(1), nbest-posteriors(1), nbest-rover(1), nbest-vocab(1), nbest2-to-nbest1(1), rescore-acoustic(1), rescore-decipher(1), rescore-reweight(1), sentid-to-sclite(1) - rescore and evaluate N-best lists
|
||
|
|
ngram(1) - apply N-gram language models
|
||
|
|
ngram-class(1) - induce word classes from N-gram statistics
|
||
|
|
ngram-count(1) - count N-grams and estimate language models
|
||
|
|
ngram-discount(7) - notes on the N-gram smoothing implementations in SRILM
|
||
|
|
ngram-format(5) - File format for ARPA backoff N-gram models
|
||
|
|
ngram-merge(1) - merge N-gram counts
|
||
|
|
pfsg-format(5) - File format for Decipher(TM) probabilistic finite-state grammars
|
||
|
|
pfsg-scripts(1), add-classes-to-pfsg(1), add-pauses-to-pfsg(1), classes-to-fsm(1), fsm-to-pfsg(1), htklat-vocab(1), make-nbest-pfsg(1), make-ngram-pfsg(1), pfsg-from-ngram(1), pfsg-to-dot(1), pfsg-to-fsm(1), pfsg-vocab(1), wlat-stats(1), wlat-to-dot(1), wlat-to-pfsg(1) - create and manipulate finite-state networks
|
||
|
|
ppl-scripts(1), add-ppls(1), compare-ppls(1), compute-best-mix(1), compute-best-sentence-mix(1), jilter-event-counts(1), hits-from-log(1), ppl-from-log(1), subtract-ppls(1) - manipulate perplexities
|
||
|
|
segment(1) - segment text using N-gram language model
|
||
|
|
segment-nbest(1) - rescore and segment N-best lists using hidden segment N-gram model
|
||
|
|
select-vocab(1) - Select a maximum-likelihood vocabulary from a mixture of corpora
|
||
|
|
srilm-faq(7), SRILM-FAQ(7) - Frequently asked questions about SRI LM tools
|
||
|
|
training-scripts(1), compute-oov-rate(1), continuous-ngram-count(1), get-gt-counts(1), make-abs-discount(1), make-batch-counts(1), make-big-lm(1), make-diacritic-map(1), make-google-ngrams(1), make-gt-discounts(1), make-kn-counts(1), make-kn-discounts(1), merge-batch-counts(1), replace-words-with-classes(1), reverse-ngram-counts(1), split-tagged-ngrams(1), reverse-text(1), tolower-ngram-counts(1), uniform-classes(1), uniq-ngram-counts(1), vp2text(1) - miscellaneous conveniences for language model training
|
||
|
|
wlat-format(5) - File format for SRILM word posterior lattices
|