Skip to content
Snippets Groups Projects
Commit e030c1a2 authored by simon devauchelle's avatar simon devauchelle
Browse files

No oovs keywords + removing ina corpus references

parent 9feaabf5
No related branches found
No related tags found
No related merge requests found
...@@ -76,11 +76,10 @@ end ...@@ -76,11 +76,10 @@ end
""" """
MFAFRDICT(path) MFAFRDICT(path)
Return the french dictionary of pronunciation as provided by MFA (french_mfa v2.0.0a) with OOVs words Return the french dictionary of pronunciation as provided by MFA (french_mfa v2.0.0a)
generated by G2P model (french_mfa) on INA Diachronic Corpus.
""" """
function MFAFRDICT(path; oovs="") function MFAFRDICT(path)
if ! isfile(path) if ! isfile(path)
mkpath(dirname(path)) mkpath(dirname(path))
dir = mktempdir() dir = mktempdir()
...@@ -96,17 +95,5 @@ function MFAFRDICT(path; oovs="") ...@@ -96,17 +95,5 @@ function MFAFRDICT(path; oovs="")
lexicon[word] = prononciations lexicon[word] = prononciations
end end
end end
# Add out-of-vocabulary words
if isfile(oovs)
open(oovs, "r") do o
for line in eachline(o)
word, pron... = split(line)
prononciations = get(lexicon, word, [])
push!(prononciations, pron)
lexicon[word] = prononciations
end
end
end
lexicon lexicon
end end
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment