MFA_FR : OOVS list of words generated from G2P models can be added to the lexicon

src/lexicons.jl

@@ -80,7 +80,7 @@ Return the french dictionary of pronunciation as provided by MFA (french_mfa v2.
 generated by G2P model (french_mfa) on INA Diachronic Corpus.
 """
 
-function MFAFRDICT(path)
+function MFAFRDICT(path; oovs="")
     if ! isfile(path)
         mkpath(dirname(path))
         dir = mktempdir()
@@ -96,5 +96,17 @@ function MFAFRDICT(path)
             lexicon[word] = prononciations
         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
 end
\ No newline at end of file