lexphon 0.1.0__tar.gz

lexphon-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

lexphon-0.1.0/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: lexphon
+Version: 0.1.0
+Summary: Lexicon-driven phonemizer and CLI built on G2Lex.
+Author: Holger Nahrstaedt
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/buchwandler/lexphon
+Project-URL: Issues, https://github.com/buchwandler/lexphon/issues
+Project-URL: Data, https://github.com/buchwandler/g2lex-data
+Keywords: g2p,phonemizer,pronunciation,ipa,g2lex,tts
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: g2lex<0.2,>=0.1.8
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: ruff>=0.16; extra == "dev"
+Requires-Dist: build>=1; extra == "dev"
+Requires-Dist: tomli>=2; python_version < "3.11" and extra == "dev"
+Dynamic: license-file
+
+# Lexphon
+
+**Lexphon** is a generic, lexicon-driven phonemizer and CLI built on [G2Lex](https://github.com/buchwandler/g2lex). It consumes released pronunciation assets and returns normalized IPA without producing Kokoro phonemes.
+
+```text
+g2lex-data producer -> G2Lex storage -> Lexphon runtime -> application adapter
+```
+
+The ownership boundary is deliberate:
+
+- `g2lex-data` obtains, transforms, validates, licenses, and publishes immutable data releases.
+- G2Lex stores and queries typed lexicon data.
+- Lexphon explicitly installs, verifies, selects, and consumes released assets.
+- KokoroG2P or another application converts generic IPA to its model-specific output.
+
+Lexphon must never contain source acquisition or G2Lex build recipes for production dictionaries.
+
+## Package layout
+
+There is intentionally no `src/` directory. The import package lives at `./lexphon`.
+
+## Install for development
+
+```bash
+python -m pip install -e ".[dev]"
+pytest
+```
+
+## Data management
+
+Catalog access and downloads are explicit. `DataStore.install()` is the network-capable provisioning operation. `Phonemizer`, lookup, token phonemization, rendering, and local store inspection never fetch a catalog or download a lexicon.
+
+```bash
+lexphon data available de-DE
+lexphon data install de-de:gold
+lexphon data list
+lexphon data info de-de:gold
+lexphon data verify de-de:gold
+lexphon data remove de-de:gold
+```
+
+Use `--catalog PATH_OR_URL` and `--data-home PATH` for a local release or alternate store. Installation downloads the manifest first, verifies manifest and asset hashes and sizes, checks catalog and manifest identity, opens the G2Lex asset, and atomically activates a complete version. Installed metadata is sufficient for offline use and a copied store can be opened without the catalog.
+
+The production German assets are `de-de:gold`, `de-de:crane`, `de-de:espeak`, and `de-de:olaph`. English CMUdict is available as `en-us:cmudict`. Membership assets can be installed for inventory use but cannot be selected as pronunciation layers.
+
+Data release versions and the Lexphon Python package version are independent. Pin the data catalog or release during provisioning, and pin the Python dependency separately.
+
+## CLI
+
+```bash
+lexphon -v de-DE "Die Leute kommen."
+lexphon -v de-DE --lexicon de-de:crane "Die Leute kommen."
+lexphon -v de-DE --lexicon de-de:crane --tag DET "die"
+lexphon -v en-US --lexicon en-us:cmudict --json "read"
+```
+
+JSON output contains the rendered IPA plus structured token fields: original text, pronunciation, source category, output alphabet, source encoding, logical lexicon ID, matched key, ordered IPA variants, selector tag, known status, and punctuation status.
+
+Optional standalone fallback is explicit:
+
+```bash
+lexphon -v de-DE --fallback espeak "unbekannteswort"
+```
+
+Fallback is disabled by default. Unknown tokens remain visible to downstream applications.
+
+## Python API
+
+```python
+from lexphon import DataStore, Phonemizer
+
+store = DataStore()
+with Phonemizer(
+    "de-DE",
+    lexicons=["de-de:gold"],
+    store=store,
+    fallback=None,
+) as g2p:
+    result = g2p.phonemize_tokens("Die Leute")
+    for token in result.tokens:
+        print(token.text, token.pronunciation, token.source, token.lexicon_id)
+```
+
+`phonemize_tokens()` is the integration API. It preserves token-level provenance, selectors, variants, punctuation, and unknown words. IPA is normalized to Unicode NFC. ARPABET and CMU-style pronunciations are converted deterministically to IPA. Unsupported alphabets and invalid pronunciation tokens raise stable Lexphon exceptions.
+
+## KokoroG2P boundary
+
+KokoroG2P should import Lexphon's Python API, use `fallback=None`, convert returned IPA using its model-specific vocabulary, and apply its own fallback, stress, ratings, and diagnostics policy. Lexphon does not import KokoroG2P, perform Kokoro validation, or download dictionaries during phonemization.

lexphon-0.1.0/README.md

@@ -0,0 +1,88 @@
+# Lexphon
+
+**Lexphon** is a generic, lexicon-driven phonemizer and CLI built on [G2Lex](https://github.com/buchwandler/g2lex). It consumes released pronunciation assets and returns normalized IPA without producing Kokoro phonemes.
+
+```text
+g2lex-data producer -> G2Lex storage -> Lexphon runtime -> application adapter
+```
+
+The ownership boundary is deliberate:
+
+- `g2lex-data` obtains, transforms, validates, licenses, and publishes immutable data releases.
+- G2Lex stores and queries typed lexicon data.
+- Lexphon explicitly installs, verifies, selects, and consumes released assets.
+- KokoroG2P or another application converts generic IPA to its model-specific output.
+
+Lexphon must never contain source acquisition or G2Lex build recipes for production dictionaries.
+
+## Package layout
+
+There is intentionally no `src/` directory. The import package lives at `./lexphon`.
+
+## Install for development
+
+```bash
+python -m pip install -e ".[dev]"
+pytest
+```
+
+## Data management
+
+Catalog access and downloads are explicit. `DataStore.install()` is the network-capable provisioning operation. `Phonemizer`, lookup, token phonemization, rendering, and local store inspection never fetch a catalog or download a lexicon.
+
+```bash
+lexphon data available de-DE
+lexphon data install de-de:gold
+lexphon data list
+lexphon data info de-de:gold
+lexphon data verify de-de:gold
+lexphon data remove de-de:gold
+```
+
+Use `--catalog PATH_OR_URL` and `--data-home PATH` for a local release or alternate store. Installation downloads the manifest first, verifies manifest and asset hashes and sizes, checks catalog and manifest identity, opens the G2Lex asset, and atomically activates a complete version. Installed metadata is sufficient for offline use and a copied store can be opened without the catalog.
+
+The production German assets are `de-de:gold`, `de-de:crane`, `de-de:espeak`, and `de-de:olaph`. English CMUdict is available as `en-us:cmudict`. Membership assets can be installed for inventory use but cannot be selected as pronunciation layers.
+
+Data release versions and the Lexphon Python package version are independent. Pin the data catalog or release during provisioning, and pin the Python dependency separately.
+
+## CLI
+
+```bash
+lexphon -v de-DE "Die Leute kommen."
+lexphon -v de-DE --lexicon de-de:crane "Die Leute kommen."
+lexphon -v de-DE --lexicon de-de:crane --tag DET "die"
+lexphon -v en-US --lexicon en-us:cmudict --json "read"
+```
+
+JSON output contains the rendered IPA plus structured token fields: original text, pronunciation, source category, output alphabet, source encoding, logical lexicon ID, matched key, ordered IPA variants, selector tag, known status, and punctuation status.
+
+Optional standalone fallback is explicit:
+
+```bash
+lexphon -v de-DE --fallback espeak "unbekannteswort"
+```
+
+Fallback is disabled by default. Unknown tokens remain visible to downstream applications.
+
+## Python API
+
+```python
+from lexphon import DataStore, Phonemizer
+
+store = DataStore()
+with Phonemizer(
+    "de-DE",
+    lexicons=["de-de:gold"],
+    store=store,
+    fallback=None,
+) as g2p:
+    result = g2p.phonemize_tokens("Die Leute")
+    for token in result.tokens:
+        print(token.text, token.pronunciation, token.source, token.lexicon_id)
+```
+
+`phonemize_tokens()` is the integration API. It preserves token-level provenance, selectors, variants, punctuation, and unknown words. IPA is normalized to Unicode NFC. ARPABET and CMU-style pronunciations are converted deterministically to IPA. Unsupported alphabets and invalid pronunciation tokens raise stable Lexphon exceptions.
+
+## KokoroG2P boundary
+
+KokoroG2P should import Lexphon's Python API, use `fallback=None`, convert returned IPA using its model-specific vocabulary, and apply its own fallback, stress, ratings, and diagnostics policy. Lexphon does not import KokoroG2P, perform Kokoro validation, or download dictionaries during phonemization.

lexphon-0.1.0/lexphon/__init__.py

@@ -0,0 +1,32 @@
+"""Lexicon-driven phonemization on top of G2Lex."""
+
+from __future__ import annotations
+
+from ._version import __version__
+from .engine import Phonemizer
+from .errors import (
+    CatalogError,
+    DataIntegrityError,
+    LexiconNotInstalledError,
+    LexiconNotUsableError,
+    LexphonError,
+    UnknownWordError,
+    UnsupportedAlphabetError,
+)
+from .models import PhonemizationResult, PronunciationToken
+from .store import DataStore
+
+__all__ = [
+    "CatalogError",
+    "DataIntegrityError",
+    "DataStore",
+    "LexiconNotInstalledError",
+    "LexiconNotUsableError",
+    "LexphonError",
+    "PhonemizationResult",
+    "Phonemizer",
+    "PronunciationToken",
+    "UnknownWordError",
+    "UnsupportedAlphabetError",
+    "__version__",
+]

lexphon-0.1.0/lexphon/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+
+raise SystemExit(main())

lexphon-0.1.0/lexphon/_version.py

@@ -0,0 +1,72 @@
+"""Small dependency-free Git-derived version helper used by setuptools."""
+
+from __future__ import annotations
+
+import os
+import re
+import subprocess
+from email.parser import Parser
+from pathlib import Path
+
+_FALLBACK = "0.1.0"
+_TAG = re.compile(
+    r"^v?(?P<base>\d+\.\d+\.\d+)(?:-(?P<count>\d+)-g(?P<sha>[0-9a-f]+))?(?P<dirty>-dirty)?$"
+)
+
+
+def _sdist_version(root: Path) -> str | None:
+    try:
+        metadata = Parser().parsestr(
+            (root / "PKG-INFO").read_text(encoding="utf-8"), headersonly=True
+        )
+    except (OSError, UnicodeError):
+        return None
+    if metadata.get("Name") != "lexphon":
+        return None
+    value = metadata.get("Version")
+    return value.strip() if value and value.strip() else None
+
+
+def get_version() -> str:
+    override = os.environ.get("LEXPHON_VERSION")
+    if override:
+        return override
+    root = Path(__file__).resolve().parents[1]
+    try:
+        text = subprocess.check_output(
+            [
+                "git",
+                "-C",
+                str(root),
+                "describe",
+                "--tags",
+                "--long",
+                "--dirty",
+                "--match",
+                "v[0-9]*",
+            ],
+            stderr=subprocess.DEVNULL,
+            text=True,
+            timeout=2,
+        ).strip()
+    except (OSError, subprocess.SubprocessError):
+        text = ""
+    match = _TAG.match(text)
+    if not match:
+        return _sdist_version(root) or _FALLBACK
+    base = match.group("base")
+    count = int(match.group("count") or 0)
+    sha = match.group("sha")
+    dirty = bool(match.group("dirty"))
+    if count == 0 and not dirty:
+        return base
+    local = []
+    if sha:
+        local.append(f"g{sha}")
+    if dirty:
+        local.append("dirty")
+    version = f"{base}.post{count}" if count else f"{base}.dev0"
+    return version + ("+" + ".".join(local) if local else "")
+
+
+__version__ = get_version()

lexphon-0.1.0/lexphon/alphabets.py

@@ -0,0 +1,109 @@
+from __future__ import annotations
+
+import re
+import unicodedata
+
+from .errors import UnsupportedAlphabetError
+
+_ARPA_CONSONANTS = {
+    "B": "b",
+    "CH": "tʃ",
+    "D": "d",
+    "DH": "ð",
+    "F": "f",
+    "G": "ɡ",
+    "HH": "h",
+    "JH": "dʒ",
+    "K": "k",
+    "L": "l",
+    "M": "m",
+    "N": "n",
+    "NG": "ŋ",
+    "P": "p",
+    "R": "ɹ",
+    "S": "s",
+    "SH": "ʃ",
+    "T": "t",
+    "TH": "θ",
+    "V": "v",
+    "W": "w",
+    "Y": "j",
+    "Z": "z",
+    "ZH": "ʒ",
+}
+_ARPA_VOWELS = {
+    "AA": "ɑ",
+    "AE": "æ",
+    "AH": "ʌ",
+    "AO": "ɔ",
+    "AW": "aʊ",
+    "AY": "aɪ",
+    "EH": "ɛ",
+    "ER": "ɝ",
+    "EY": "eɪ",
+    "IH": "ɪ",
+    "IY": "i",
+    "OW": "oʊ",
+    "OY": "ɔɪ",
+    "UH": "ʊ",
+    "UW": "u",
+    "AX": "ə",
+    "AXR": "ɚ",
+    "IX": "ɨ",
+}
+_ARPA_TOKEN = re.compile(r"^(?P<phoneme>[A-Z]+)(?P<stress>[012])?$")
+
+
+def arpabet_to_ipa(value: str) -> str:
+    """Convert CMU-style ARPABET to deterministic broad IPA."""
+    if not isinstance(value, str) or not value.strip():
+        raise UnsupportedAlphabetError("ARPABET pronunciation must contain phone tokens")
+    segments: list[str] = []
+    vowel_indices: list[int] = []
+    stressed: list[tuple[int, str]] = []
+    for raw in value.split():
+        match = _ARPA_TOKEN.fullmatch(raw.upper())
+        if not match:
+            raise UnsupportedAlphabetError(f"invalid ARPABET token: {raw!r}")
+        symbol = match.group("phoneme")
+        stress = match.group("stress")
+        if symbol in _ARPA_VOWELS:
+            ipa = _ARPA_VOWELS[symbol]
+            if symbol == "AH" and stress == "0":
+                ipa = "ə"
+            elif symbol == "ER" and stress == "0":
+                ipa = "ɚ"
+            vowel_ordinal = len(vowel_indices)
+            if stress in {"1", "2"}:
+                stressed.append((vowel_ordinal, "ˈ" if stress == "1" else "ˌ"))
+            vowel_indices.append(len(segments))
+            segments.append(ipa)
+        elif symbol in _ARPA_CONSONANTS:
+            if stress is not None:
+                raise UnsupportedAlphabetError(f"stress on ARPABET consonant: {raw!r}")
+            segments.append(_ARPA_CONSONANTS[symbol])
+        else:
+            raise UnsupportedAlphabetError(f"unsupported ARPABET phoneme: {symbol}")
+
+    insertions: dict[int, list[str]] = {}
+    for vowel_ordinal, marker in stressed:
+        position = 0 if vowel_ordinal == 0 else vowel_indices[vowel_ordinal - 1] + 1
+        insertions.setdefault(position, []).append(marker)
+
+    output: list[str] = []
+    for index, segment in enumerate(segments):
+        output.extend(insertions.get(index, ()))
+        output.append(segment)
+    output.extend(insertions.get(len(segments), ()))
+    return unicodedata.normalize("NFC", "".join(output))
+
+
+def to_ipa(value: str, encoding: str) -> str:
+    if not isinstance(value, str) or not value:
+        raise UnsupportedAlphabetError("pronunciation must be a non-empty string")
+    key = encoding.casefold().replace("-", "")
+    if key in {"ipa", "unicodeipa"}:
+        return unicodedata.normalize("NFC", value)
+    if key in {"arpabet", "cmu", "cmudict"}:
+        return arpabet_to_ipa(value)
+    raise UnsupportedAlphabetError(f"unsupported pronunciation encoding: {encoding!r}")