Add C++ and Python API for Kokoro 1.0 multilingual TTS model (#1795)

sherpa-onnx/csrc/offline-tts-kokoro-model-config.cc

@@ -8,6 +8,7 @@
 
 #include "sherpa-onnx/csrc/file-utils.h"
 #include "sherpa-onnx/csrc/macros.h"
+#include "sherpa-onnx/csrc/text-utils.h"
 
 namespace sherpa_onnx {
 
@@ -17,8 +18,16 @@ void OfflineTtsKokoroModelConfig::Register(ParseOptions *po) {
                "Path to voices.bin for Kokoro models");
   po->Register("kokoro-tokens", &tokens,
                "Path to tokens.txt for Kokoro models");
+  po->Register(
+      "kokoro-lexicon", &lexicon,
+      "Path to lexicon.txt for Kokoro models. Used only for Kokoro >= v1.0"
+      "You can pass multiple files, separated by ','. Example: "
+      "./lexicon-us-en.txt,./lexicon-zh.txt");
   po->Register("kokoro-data-dir", &data_dir,
                "Path to the directory containing dict for espeak-ng.");
+  po->Register("kokoro-dict-dir", &dict_dir,
+               "Path to the directory containing dict for jieba. "
+               "Used only for Kokoro >= v1.0");
   po->Register("kokoro-length-scale", &length_scale,
                "Speech speed. Larger->Slower; Smaller->faster.");
 }
@@ -44,6 +53,19 @@ bool OfflineTtsKokoroModelConfig::Validate() const {
     return false;
   }
 
+  if (!lexicon.empty()) {
+    std::vector<std::string> files;
+    SplitStringToVector(lexicon, ",", false, &files);
+    for (const auto &f : files) {
+      if (!FileExists(f)) {
+        SHERPA_ONNX_LOGE(
+            "lexicon '%s' does not exist. Please re-check --kokoro-lexicon",
+            f.c_str());
+        return false;
+      }
+    }
+  }
+
   if (data_dir.empty()) {
     SHERPA_ONNX_LOGE("Please provide --kokoro-data-dir");
     return false;
@@ -77,6 +99,21 @@ bool OfflineTtsKokoroModelConfig::Validate() const {
     return false;
   }
 
+  if (!dict_dir.empty()) {
+    std::vector<std::string> required_files = {
+        "jieba.dict.utf8", "hmm_model.utf8",  "user.dict.utf8",
+        "idf.utf8",        "stop_words.utf8",
+    };
+
+    for (const auto &f : required_files) {
+      if (!FileExists(dict_dir + "/" + f)) {
+        SHERPA_ONNX_LOGE("'%s/%s' does not exist. Please check kokoro-dict-dir",
+                         dict_dir.c_str(), f.c_str());
+        return false;
+      }
+    }
+  }
+
   return true;
 }
 
@@ -87,7 +124,9 @@ std::string OfflineTtsKokoroModelConfig::ToString() const {
   os << "model=\"" << model << "\", ";
   os << "voices=\"" << voices << "\", ";
   os << "tokens=\"" << tokens << "\", ";
+  os << "lexicon=\"" << lexicon << "\", ";
   os << "data_dir=\"" << data_dir << "\", ";
+  os << "dict_dir=\"" << dict_dir << "\", ";
   os << "length_scale=" << length_scale << ")";
 
   return os.str();