Skip to content

Fix: load consonants from YAML file #1855

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Cadlaxa wants to merge 18 commits into
base: master
Choose a base branch
from
Open

Fix: load consonants from YAML file #1855

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
de5bd13
fix yaml timings entry overrides with new instance of the phonemizer
Cadlaxa Nov 28, 2025
17e98c5
Merge branch 'master' of https://github.com/stakira/OpenUtau into SBP…
Cadlaxa Nov 30, 2025
be0490c
Fix: load consonants from YAML file
Cadlaxa Nov 30, 2025
2c54121
Fixes
Cadlaxa Dec 6, 2025
aa43281
Fixes to PhonemeIsPresent boolean
Cadlaxa Dec 23, 2025
439e0ee
[ARPA+] split phonemes when splitted in phonetic hints
Cadlaxa Dec 30, 2025
445dd96
Better PhonemeIsPresent handling + fixes
Cadlaxa Dec 30, 2025
05911ee
Update ARPA+ text file
Cadlaxa Dec 30, 2025
9e29b1e
Fixes
Cadlaxa Dec 30, 2025
44668b8
Fix test file
Cadlaxa Dec 30, 2025
e20038b
Fix ARPA+ phonetic hints
Cadlaxa Dec 30, 2025
a4d3ec2
Update ARPA+ test file
Cadlaxa Dec 30, 2025
a3077ab
[ARPA+] fix conditionals
Cadlaxa Dec 31, 2025
e107325
fix hasVC bool conditions
Cadlaxa Dec 31, 2025
0de8ccc
code cleanup
Cadlaxa Dec 31, 2025
c805bb5
[ARPA+] CCV fix + code cleanup
Cadlaxa Jan 3, 2026
621efd5
Much more robust Yaml Fallbacks
Cadlaxa Jan 3, 2026
df1d9d1
Merge branch 'master' of https://github.com/stakira/OpenUtau into SBP…
Cadlaxa Jan 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
239 changes: 133 additions & 106 deletions OpenUtau.Plugin.Builtin/ArpasingPlusPhonemizer.cs
View file
Open in desktop

Large diffs are not rendered by default.

13 changes: 10 additions & 3 deletions OpenUtau.Plugin.Builtin/EnXSampaPhonemizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1162,13 +1162,13 @@ protected override string ValidateAlias(string alias) {
}

if (isReplacements) {
foreach (var syllable in replacements) {
foreach (var syllable in replacements.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(syllable.Key, syllable.Value);
}
}

if (isfallbacks) {
foreach (var syllable in fallbacks) {
foreach (var syllable in fallbacks.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(syllable.Key, syllable.Value);
}
}
Expand Down Expand Up @@ -1200,7 +1200,14 @@ protected override string ValidateAlias(string alias) {
}

bool PhonemeIsPresent(string alias, string phoneme) {
return Regex.IsMatch(alias, $@"\b{Regex.Escape(phoneme)}\b");
if (string.IsNullOrEmpty(alias) || string.IsNullOrEmpty(phoneme))
return false;

// Exact token match
if (alias == phoneme)
return true;

return alias.EndsWith(phoneme);
}

private bool PhonemeHasEndingSuffix(string alias, string phoneme) {
Expand Down
62 changes: 46 additions & 16 deletions OpenUtau.Plugin.Builtin/EnglishCpVPhonemizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ public class EnglishCpVPhonemizer : SyllableBasedPhonemizer {
};
private static string[] diphthongs = { "ay", "ey", "oy", "aw", "ow" };
private static string[] c_cR = { "n" };
private static string[] consonants = "".Split(',');
private static string[] consonants = "b,ch,d,dh,dr,dx,f,g,hh,jh,k,l,m,n,ng,p,q,r,s,sh,t,th,tr,v,w,y,z".Split(',');
private static string[] affricate = "".Split(',');
private static string[] fricative = "".Split(',');
private static string[] aspirate = "".Split(',');
Expand Down Expand Up @@ -423,6 +423,16 @@ public override void SetSinger(USinger singer) {
stop = stops.Distinct().ToArray();
tap = taps.Distinct().ToArray();
affricate = affricates.Distinct().ToArray();
/*consonants = fricatives
.Concat(aspirates)
.Concat(semivowels)
.Concat(liquids)
.Concat(nasals)
.Concat(stop)
.Concat(tap)
.Concat(affricate)
.Distinct()
.ToArray();*/
// Load diphthong exceptions
try {
var allDiphthongs = data.symbols
Expand Down Expand Up @@ -1075,16 +1085,34 @@ private string AliasFormat(string alias, string type, int tone, string prevV) {
protected override string ValidateAlias(string alias) {

// VALIDATE ALIAS DEPENDING ON METHOD
if (isMissingVPhonemes || isMissingCPhonemes || isTimitPhonemes) {
foreach (var phoneme in missingVphonemes.Concat(missingCphonemes).Concat(timitphonemes)) {
alias = alias.Replace(phoneme.Key, phoneme.Value);
if (isTimitPhonemes) {
foreach (var fb in timitphonemes.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(fb.Key, fb.Value);
}
}
if (isMissingVPhonemes) {
foreach (var fb in missingVphonemes.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(fb.Key, fb.Value);
}
}
if (isMissingCPhonemes) {
foreach (var fb in missingCphonemes.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(fb.Key, fb.Value);
}
}
return alias;

}

bool PhonemeIsPresent(string alias, string phoneme) {
return Regex.IsMatch(alias, $@"\b{Regex.Escape(phoneme)}\b");
if (string.IsNullOrEmpty(alias) || string.IsNullOrEmpty(phoneme))
return false;

// Exact token match
if (alias == phoneme)
return true;

return alias.EndsWith(phoneme);
}

private bool PhonemeHasEndingSuffix(string alias, string phoneme) {
Expand Down Expand Up @@ -1121,17 +1149,7 @@ protected override double GetTransitionBasicLengthMs(string alias = "") {
.Concat(affricate)
.Distinct(); // Ensure no duplicates

foreach (var c in allConsonants) {
if (PhonemeHasEndingSuffix(alias, c)) {
return base.GetTransitionBasicLengthMs() * 0.5;
}
}

foreach (var v in vowels) {
if (alias.EndsWith("-")) {
return base.GetTransitionBasicLengthMs() * 0.5;
}
}


// consonant timings

Expand All @@ -1144,6 +1162,18 @@ protected override double GetTransitionBasicLengthMs(string alias = "") {
}
}

foreach (var c in allConsonants) {
if (PhonemeHasEndingSuffix(alias, c)) {
return base.GetTransitionBasicLengthMs() * 0.5;
}
}

foreach (var v in vowels) {
if (alias.EndsWith("-")) {
return base.GetTransitionBasicLengthMs() * 0.5;
}
}

foreach (var c in fricative) {
if (PhonemeIsPresent(alias, c)) {
return base.GetTransitionBasicLengthMs() * fricative_def;
Expand Down
2 changes: 1 addition & 1 deletion OpenUtau.Plugin.Builtin/EnglishVCCVPhonemizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1014,7 +1014,7 @@ protected override string ValidateAlias(string alias) {
// alias = alias.Replace(consonant, "hh");
//}
if (isReplacements) {
foreach (var syllable in replacements) {
foreach (var syllable in replacements.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(syllable.Key, syllable.Value);
}
}
Expand Down
39 changes: 31 additions & 8 deletions OpenUtau.Plugin.Builtin/FilipinoPhonemizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -350,6 +350,16 @@ public override void SetSinger(USinger singer) {
stop = stops.Distinct().ToArray();
tap = taps.Distinct().ToArray();
affricate = affricates.Distinct().ToArray();
consonants = fricatives
.Concat(aspirates)
.Concat(semivowels)
.Concat(liquids)
.Concat(nasals)
.Concat(stop)
.Concat(tap)
.Concat(affricate)
.Distinct()
.ToArray();
// Load replacements
try {
if (data?.replacements != null && data.replacements.Any() == true) {
Expand Down Expand Up @@ -569,9 +579,9 @@ protected override List<string> ProcessSyllable(Syllable syllable) {
lastC = 0;
} else {
/// CCV and CV
if (HasOto(ccv, syllable.vowelTone) || HasOto(ValidateAlias(ccv), syllable.vowelTone) || HasOto(ccv1, syllable.vowelTone) || HasOto(ValidateAlias(ccv1), syllable.vowelTone) && !ccvException.Contains(cc[0])) {
if (HasOto(ccv, syllable.vowelTone) || HasOto(ValidateAlias(ccv), syllable.vowelTone) || HasOto(ccv1, syllable.vowelTone) || HasOto(ValidateAlias(ccv1), syllable.vowelTone)) {
basePhoneme = AliasFormat($"{string.Join("", cc)} {v}", "dynMid", syllable.vowelTone, "");
//lastC = 0;
lastC = 0;
} else if (HasOto(crv, syllable.vowelTone) || HasOto(ValidateAlias(crv), syllable.vowelTone) || HasOto(crv1, syllable.vowelTone) || HasOto(ValidateAlias(crv1), syllable.vowelTone)) {
basePhoneme = AliasFormat($"{cc.Last()} {v}", "dynMid", syllable.vowelTone, "");
} else {
Expand All @@ -594,7 +604,7 @@ protected override List<string> ProcessSyllable(Syllable syllable) {
var cv = $"{cc.Last()}{v}";
for (var i = firstC; i < cc.Length - 1; i++) {
/// CCV
if (CurrentWordCc.Length >= 2 && !ccvException.Contains(cc[i])) {
if (CurrentWordCc.Length >= 2) {
if (HasOto(ccv, syllable.vowelTone) || HasOto(ValidateAlias(ccv), syllable.vowelTone) || HasOto(ccv1, syllable.vowelTone) || HasOto(ValidateAlias(ccv1), syllable.vowelTone)) {
basePhoneme = AliasFormat($"{string.Join("", cc)} {v}", "dynMid", syllable.vowelTone, "");
lastC = i;
Expand Down Expand Up @@ -647,7 +657,7 @@ protected override List<string> ProcessSyllable(Syllable syllable) {
var ccv = $"{string.Join("", cc)} {v}";
var ccv1 = $"{string.Join("", cc)}{v}";
/// CCV
if (CurrentWordCc.Length >= 2 && !ccvException.Contains(cc[i])) {
if (CurrentWordCc.Length >= 2) {
if (HasOto(ccv, syllable.vowelTone) || HasOto(ValidateAlias(ccv), syllable.vowelTone) || HasOto(ccv1, syllable.vowelTone) || HasOto(ValidateAlias(ccv1), syllable.vowelTone)) {
basePhoneme = AliasFormat($"{string.Join("", cc)} {v}", "dynMid", syllable.vowelTone, "");
lastC = i;
Expand Down Expand Up @@ -1217,17 +1227,30 @@ private string AliasFormat(string alias, string type, int tone, string prevV) {
protected override string ValidateAlias(string alias) {

// VALIDATE ALIAS DEPENDING ON METHOD
if (isMissingVPhonemes || isMissingCPhonemes) {
foreach (var phoneme in missingVphonemes.Concat(missingCphonemes)) {
alias = alias.Replace(phoneme.Key, phoneme.Value);
if (isMissingVPhonemes) {
foreach (var fb in missingVphonemes.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(fb.Key, fb.Value);
}
}
if (isMissingCPhonemes) {
foreach (var fb in missingCphonemes.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(fb.Key, fb.Value);
}
}
return alias;

return base.ValidateAlias(alias);
}

bool PhonemeIsPresent(string alias, string phoneme) {
return Regex.IsMatch(alias, $@"\b{Regex.Escape(phoneme)}\b");
if (string.IsNullOrEmpty(alias) || string.IsNullOrEmpty(phoneme))
return false;

// Exact token match
if (alias == phoneme)
return true;

return alias.EndsWith(phoneme);
}

private bool PhonemeHasEndingSuffix(string alias, string phoneme) {
Expand Down
2 changes: 1 addition & 1 deletion OpenUtau.Plugin.Builtin/GermanVCCVPhonemizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -658,7 +658,7 @@ protected override string ValidateAlias(string alias) {
}

if (isReplacements) {
foreach (var syllable in replacements) {
foreach (var syllable in replacements.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(syllable.Key, syllable.Value);
}
}
Expand Down
15 changes: 13 additions & 2 deletions OpenUtau.Plugin.Builtin/SpanishVCCVPhonemizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,6 @@ public class SpanishVCCVPhonemizer : SyllableBasedPhonemizer {
.ToDictionary(parts => parts[0], parts => parts[1]);
private bool isReplacements = false;


protected override IG2p LoadBaseDictionary() {
var g2ps = new List<IG2p>();

Expand Down Expand Up @@ -308,12 +307,18 @@ protected override List<string> ProcessSyllable(Syllable syllable) {
var prevV = string.IsNullOrEmpty(replacedPrevV) ? "" : replacedPrevV;
string v = ReplacePhoneme(syllable.v, syllable.vowelTone);
string[] cc = syllable.cc.Select(ReplacePhoneme).ToArray();

string basePhoneme;
var phonemes = new List<string>();
var lastC = cc.Length - 1;
var firstC = 0;

foreach (var entry in replacements) {
if (!HasOto(entry.Key, syllable.tone) && !HasOto(entry.Key, syllable.tone)) {
isReplacements = true;
break;
}
}

if (syllable.IsStartingV) {
var rcv = $"- {v}";
var rcv2 = $"-{v}";
Expand Down Expand Up @@ -644,6 +649,12 @@ protected override string ValidateAlias(string alias) {
//foreach (var consonant in new[] { "y" }) {
// alias = alias.Replace("y", "i");
// }
if (isReplacements) {
foreach (var syllable in replacements.OrderByDescending(f => f.Key.Length)) {
alias = alias.Replace(syllable.Key, syllable.Value);
}
}

foreach (var consonant in new[] { "I" }) {
alias = alias.Replace("I", "y");
}
Expand Down
Loading