Index: source/data/translit/zu_zu_FONIPA.txt |
diff --git a/source/data/translit/zu_zu_FONIPA.txt b/source/data/translit/zu_zu_FONIPA.txt |
new file mode 100644 |
index 0000000000000000000000000000000000000000..530d9a0fbc18782cf5b7bfcf56093120bdc6a0cd |
--- /dev/null |
+++ b/source/data/translit/zu_zu_FONIPA.txt |
@@ -0,0 +1,78 @@ |
+# © 2016 and later: Unicode, Inc. and others. |
+# License & terms of use: http://www.unicode.org/copyright.html#License |
+# |
+# File: zu_zu_FONIPA.txt |
+# Generated from CLDR |
+# |
+ |
+# Pronunciation rules for isiZulu. |
+# |
+# Author: mjansche@google.com (Martin Jansche) |
+# |
+# These rules transcribe isiZulu into the phoneme inventory used within the |
+# NCHLT Speech Corpus (https://sites.google.com/site/nchltspeechcorpus/home). |
+# |
+# The rules were tested using the NCHLT-inlang isiZulu pronunciation dictionary |
+# (http://rma.nwu.ac.za/index.php/resource-catalogue/nchlt-inlang-dictionaries.html). |
+# They correctly account for all 15,000 entries in the dictionary. |
+# |
+# The NCHLT 2013 phone set does not indicate tone in any way. Transcription of |
+# tone is out of scope without a dictionary, since tone is generally not |
+# indicated in the orthography. Nasal clicks are not treated as separated |
+# phonemes in the NCHLT 2013 phone set and are transcribed as a sequence of |
+# nasal plus click instead. |
+# |
+# One minor notational deviation from the NCHLT 2013 phone set is that we use a |
+# tie bar within the complex (depressor) clicks, e.g. ɡ\u0361ǀ instead of ɡǀ, to |
+# avoid ambiguity and make the phoneme inventory uniquely decodable. |
+::Lower; |
+tsh → t\u0361ʃʼ; |
+bh → b; |
+ch → ǀʰ; |
+dl → ɮ; |
+gc → ɡ\u0361ǀ; |
+gq → ɡ\u0361ǃ; |
+gx → ɡ\u0361ǁ; |
+hh → ɦ; # To investigate: /ɦ/ and /h/ may be switched in the NCHLT dictionary. |
+hl → ɬ; |
+kh → kʰ; |
+kl → k\u0361ɬ; |
+ny → ɲ; |
+ph → pʰ; |
+qh → ǃʰ; |
+n { sh → t\u0361sʼ; |
+sh → ʃ; |
+th → tʰ; |
+xh → ǁʰ; |
+a → a; |
+m { b → b; |
+b → ɓ; |
+c → ǀ; |
+d → d; |
+e → ɛ; |
+f → f; |
+g → ɡ; |
+h → h; |
+i → i; |
+j → d\u0361ʒ; |
+k → k; |
+l → l; |
+m → m; |
+[$] { n } gc → n; |
+n } [gk] → ŋ; |
+n } j → ɲ; |
+n → n; |
+o → ɔ; |
+p → pʼ; |
+q → ǃ; |
+n { s → t\u0361sʼ; |
+s → s; |
+t → tʼ; |
+u → u; |
+v → v; |
+w → w; |
+x → ǁ; |
+y → j; |
+n { z → d\u0361z; |
+z → z; |
+ |