Merge branch 'add_timit_alignments' into ina_diachronic_corpus

merge

src/SpeechDatasets.jl

@@ -31,6 +31,7 @@ export
     # Lexicon
     CMUDICT,
     TIMITDICT,
+    MFAFRDICT,
 
     # Dataset
     dataset

src/lexicons.jl

@@ -2,7 +2,7 @@
 
 
 const CMUDICT_URL = "http://svn.code.sf.net/p/cmusphinx/code/trunk/cmudict/sphinxdict/cmudict_SPHINX_40"
-
+const FRMFA_DICT_URL = "https://raw.githubusercontent.com/MontrealCorpusTools/mfa-models/main/dictionary/french/mfa/french_mfa.dict"
 
 function normalizeword(word)
     String(uppercase(word))
@@ -71,3 +71,42 @@ function TIMITDICT(timitdir)
     end
     lexicon
 end
+
+
+"""
+    MFAFRDICT(path)
+
+Return the french dictionary of pronunciation as provided by MFA (french_mfa v2.0.0a) with OOVs words
+generated by G2P model (french_mfa) on INA Diachronic Corpus.
+"""
+
+function MFAFRDICT(path; oovs="")
+    if ! isfile(path)
+        mkpath(dirname(path))
+        dir = mktempdir()
+        run(`wget -P $dir $FRMFA_DICT_URL`)
+        mv(joinpath(dir, "french_mfa.dict"), path)
+    end
+    lexicon = Dict()
+    open(path, "r") do f
+        for line in eachline(f)
+            word, pron... = split(line)
+            prononciations = get(lexicon, word, [])
+            push!(prononciations, pron)
+            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