Use piper-phonemize to convert text to token IDs (#453)

sherpa-onnx/csrc/piper-phonemize-lexicon.h

@@ -0,0 +1,41 @@
+// sherpa-onnx/csrc/piper-phonemize-lexicon.h
+//
+// Copyright (c)  2022-2023  Xiaomi Corporation
+
+#ifndef SHERPA_ONNX_CSRC_PIPER_PHONEMIZE_LEXICON_H_
+#define SHERPA_ONNX_CSRC_PIPER_PHONEMIZE_LEXICON_H_
+
+#include <string>
+#include <unordered_map>
+#include <vector>
+
+#if __ANDROID_API__ >= 9
+#include "android/asset_manager.h"
+#include "android/asset_manager_jni.h"
+#endif
+
+#include "sherpa-onnx/csrc/offline-tts-frontend.h"
+
+namespace sherpa_onnx {
+
+class PiperPhonemizeLexicon : public OfflineTtsFrontend {
+ public:
+  PiperPhonemizeLexicon(const std::string &tokens, const std::string &data_dir);
+
+#if __ANDROID_API__ >= 9
+  PiperPhonemizeLexicon(AAssetManager *mgr, const std::string &tokens,
+                        const std::string &data_dir);
+#endif
+
+  std::vector<std::vector<int64_t>> ConvertTextToTokenIds(
+      const std::string &text, const std::string &voice = "") const override;
+
+ private:
+  std::string data_dir_;
+  // map unicode codepoint to an integer ID
+  std::unordered_map<char32_t, int32_t> token2id_;
+};
+
+}  // namespace sherpa_onnx
+
+#endif  // SHERPA_ONNX_CSRC_PIPER_PHONEMIZE_LEXICON_H_