Add files

.pre-commit-config.yaml

@@ -0,0 +1,33 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.6
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-pytz",
+            "types-PyYAML",
+            "types-requests",
+          ]

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "ms-python.python",
+        "charliermarsh.ruff",
+        "streetsidesoftware.code-spell-checker",
+        "tamasfe.even-better-toml"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,17 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit",
+            "source.organizeImports": "explicit"
+        }
+    },
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "notebook.output.scrolling": true,
+    "notebook.formatOnSave.enabled": true
+}

app.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+
+import gradio as gr
+import numpy as np
+import spaces
+from kokoro import KPipeline
+
+pipeline = KPipeline(lang_code="j")
+
+VOICES = [
+    "jf_alpha",
+    "jf_gongitsune",
+    "jf_nezumi",
+    "jf_tebukuro",
+    "jm_kumo",
+]
+
+
+@spaces.GPU(duration=20)
+def run(text: str, voice: str, speed: float) -> tuple[tuple[int, np.ndarray], str]:
+    generator = pipeline(
+        text,
+        voice=voice,
+        speed=speed,
+        split_pattern=r"\n+",
+    )
+    _, ps, audio = next(generator)
+    return (24000, audio.numpy()), ps
+
+
+with gr.Blocks(css_paths="style.css") as demo:
+    gr.Markdown("# Kokoro (ja)")
+    with gr.Row():
+        with gr.Column():
+            input_text = gr.Textbox(label="Input Text")
+            voice = gr.Dropdown(label="Voice", choices=VOICES, value=VOICES[0])
+            speed = gr.Slider(label="Speed", minimum=0.5, maximum=2.0, step=0.1, value=1.0)
+            run_button = gr.Button()
+        with gr.Column():
+            output_audio = gr.Audio(label="Output Audio", autoplay=True)
+            output_tokens = gr.Textbox(label="Output Tokens")
+    gr.Examples(
+        examples=[
+            "どうもこんにちは。今日はいい天気ですね。",
+            "隣の竹垣に竹立てかけたのは隣の竹垣に竹立てかけたかったからと骨粗鬆症の東京特許許可局局長がマサチューセッツ州の美術室で魔術師が呪術師と手術中に供述。",
+            "李も桃も桃のうち",
+            "隣の客はよく柿食う客だ",
+            "裏庭には二羽、庭には二羽、鶏がいる。",
+            "貴社の記者が汽車で帰社した。橋の端にある箸。石でできた医師。お食事券にまつわる汚職事件。",
+        ],
+        inputs=input_text,
+    )
+
+    run_button.click(
+        fn=run,
+        inputs=[input_text, voice, speed],
+        outputs=[output_audio, output_tokens],
+    )
+
+if __name__ == "__main__":
+    demo.launch()

pyproject.toml

@@ -0,0 +1,56 @@
+[project]
+name = "kokoro-ja"
+version = "0.1.0"
+description = ""
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "gradio>=5.16.0",
+    "hf-transfer>=0.1.9",
+    "kokoro>=0.7.16",
+    "misaki[ja]>=0.7.17",
+    "spaces>=0.32.0",
+    "torch==2.4.0",
+]
+
+[tool.ruff]
+line-length = 119
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = [
+    "COM812", # missing-trailing-comma
+    "D203",   # one-blank-line-before-class
+    "D213",   # multi-line-summary-second-line
+    "E501",   # line-too-long
+    "SIM117", # multiple-with-statements
+]
+extend-ignore = [
+    "D100",    # undocumented-public-module
+    "D101",    # undocumented-public-class
+    "D102",    # undocumented-public-method
+    "D103",    # undocumented-public-function
+    "D104",    # undocumented-public-package
+    "D105",    # undocumented-magic-method
+    "D107",    # undocumented-public-init
+    "EM101",   # raw-string-in-exception
+    "FBT001",  # boolean-type-hint-positional-argument
+    "FBT002",  # boolean-default-value-positional-argument
+    "PD901",   # pandas-df-variable-name
+    "PGH003",  # blanket-type-ignore
+    "PLR0913", # too-many-arguments
+    "PLR0915", # too-many-statements
+    "TRY003",  # raise-vanilla-args
+]
+unfixable = [
+    "F401", # unused-import
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.per-file-ignores]
+"*.ipynb" = ["T201"]
+
+[tool.ruff.format]
+docstring-code-format = true

requirements.txt

@@ -0,0 +1,416 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+aiofiles==23.2.1
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.8.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+attrs==25.1.0
+    # via
+    #   clldutils
+    #   csvw
+    #   jsonschema
+    #   phonemizer-fork
+    #   referencing
+babel==2.17.0
+    # via csvw
+blis==1.2.0
+    # via thinc
+catalogue==2.0.10
+    # via
+    #   spacy
+    #   srsly
+    #   thinc
+certifi==2025.1.31
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.1
+    # via requests
+click==8.1.8
+    # via
+    #   typer
+    #   uvicorn
+clldutils==3.21.0
+    # via segments
+cloudpathlib==0.20.0
+    # via weasel
+colorama==0.4.6
+    # via csvw
+colorlog==6.9.0
+    # via clldutils
+confection==0.1.5
+    # via
+    #   thinc
+    #   weasel
+csvw==3.5.1
+    # via segments
+curated-tokenizers==0.0.9
+    # via spacy-curated-transformers
+curated-transformers==0.1.1
+    # via spacy-curated-transformers
+cymem==2.0.11
+    # via
+    #   preshed
+    #   spacy
+    #   thinc
+dlinfo==2.0.0
+    # via phonemizer-fork
+docopt==0.6.2
+    # via num2words
+espeakng-loader==0.2.4
+    # via misaki
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.8
+    # via gradio
+ffmpy==0.5.0
+    # via gradio
+filelock==3.17.0
+    # via
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+fsspec==2025.2.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+fugashi==1.4.0
+    # via misaki
+gradio==5.16.0
+    # via
+    #   kokoro-ja (pyproject.toml)
+    #   spaces
+gradio-client==1.7.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.9
+    # via kokoro-ja (pyproject.toml)
+httpcore==1.0.7
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   safehttpx
+    #   spaces
+huggingface-hub==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   kokoro
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+isodate==0.7.2
+    # via
+    #   csvw
+    #   rdflib
+jaconv==0.4.0
+    # via misaki
+jinja2==3.1.5
+    # via
+    #   gradio
+    #   spacy
+    #   torch
+joblib==1.4.2
+    # via phonemizer-fork
+jsonschema==4.23.0
+    # via csvw
+jsonschema-specifications==2024.10.1
+    # via jsonschema
+kokoro==0.7.16
+    # via kokoro-ja (pyproject.toml)
+langcodes==3.5.0
+    # via spacy
+language-data==1.3.0
+    # via langcodes
+language-tags==1.2.0
+    # via csvw
+loguru==0.7.3
+    # via kokoro
+lxml==5.3.1
+    # via clldutils
+marisa-trie==1.2.1
+    # via language-data
+markdown==3.7
+    # via clldutils
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   clldutils
+    #   gradio
+    #   jinja2
+mdurl==0.1.2
+    # via markdown-it-py
+misaki==0.7.17
+    # via
+    #   kokoro-ja (pyproject.toml)
+    #   kokoro
+mojimoji==0.0.13
+    # via misaki
+mpmath==1.3.0
+    # via sympy
+murmurhash==1.0.12
+    # via
+    #   preshed
+    #   spacy
+    #   thinc
+networkx==3.4.2
+    # via torch
+num2words==0.5.14
+    # via misaki
+numpy==1.26.4
+    # via
+    #   blis
+    #   gradio
+    #   kokoro
+    #   pandas
+    #   scipy
+    #   spacy
+    #   thinc
+    #   transformers
+nvidia-cublas-cu12==12.1.3.1
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.1.105
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.1.105
+    # via torch
+nvidia-cuda-runtime-cu12==12.1.105
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.0.2.54
+    # via torch
+nvidia-curand-cu12==10.3.2.106
+    # via torch
+nvidia-cusolver-cu12==11.4.5.107
+    # via torch
+nvidia-cusparse-cu12==12.1.0.106
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-nccl-cu12==2.20.5
+    # via torch
+nvidia-nvjitlink-cu12==12.8.61
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+nvidia-nvtx-cu12==12.1.105
+    # via torch
+orjson==3.10.15
+    # via gradio
+packaging==24.2
+    # via
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   spaces
+    #   spacy
+    #   thinc
+    #   transformers
+    #   weasel
+pandas==2.2.3
+    # via gradio
+phonemizer-fork==3.3.2
+    # via misaki
+pillow==11.1.0
+    # via gradio
+preshed==3.0.9
+    # via
+    #   spacy
+    #   thinc
+psutil==5.9.8
+    # via spaces
+pydantic==2.10.6
+    # via
+    #   confection
+    #   fastapi
+    #   gradio
+    #   spaces
+    #   spacy
+    #   thinc
+    #   weasel
+pydantic-core==2.27.2
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.19.1
+    # via rich
+pylatexenc==2.10
+    # via clldutils
+pyparsing==3.2.1
+    # via rdflib
+python-dateutil==2.9.0.post0
+    # via
+    #   clldutils
+    #   csvw
+    #   pandas
+python-multipart==0.0.20
+    # via gradio
+pytz==2025.1
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+rdflib==7.1.3
+    # via csvw
+referencing==0.36.2
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
+regex==2024.11.6
+    # via
+    #   curated-tokenizers
+    #   misaki
+    #   segments
+    #   transformers
+requests==2.32.3
+    # via
+    #   csvw
+    #   huggingface-hub
+    #   spaces
+    #   spacy
+    #   transformers
+    #   weasel
+rfc3986==1.5.0
+    # via csvw
+rich==13.9.4
+    # via typer
+rpds-py==0.22.3
+    # via
+    #   jsonschema
+    #   referencing
+ruff==0.9.6
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+safetensors==0.5.2
+    # via transformers
+scipy==1.15.2
+    # via kokoro
+segments==2.2.1
+    # via phonemizer-fork
+semantic-version==2.10.0
+    # via gradio
+setuptools==75.8.0
+    # via
+    #   marisa-trie
+    #   spacy
+    #   thinc
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via python-dateutil
+smart-open==7.1.0
+    # via weasel
+sniffio==1.3.1
+    # via anyio
+spaces==0.32.0
+    # via kokoro-ja (pyproject.toml)
+spacy==3.8.4
+    # via misaki
+spacy-curated-transformers==0.3.0
+    # via misaki
+spacy-legacy==3.0.12
+    # via spacy
+spacy-loggers==1.0.5
+    # via spacy
+srsly==2.5.1
+    # via
+    #   confection
+    #   spacy
+    #   thinc
+    #   weasel
+starlette==0.45.3
+    # via
+    #   fastapi
+    #   gradio
+sympy==1.13.3
+    # via torch
+tabulate==0.9.0
+    # via clldutils
+thinc==8.3.4
+    # via spacy
+tokenizers==0.21.0
+    # via transformers
+tomlkit==0.13.2
+    # via gradio
+torch==2.4.0
+    # via
+    #   kokoro-ja (pyproject.toml)
+    #   curated-transformers
+    #   kokoro
+    #   spacy-curated-transformers
+tqdm==4.67.1
+    # via
+    #   huggingface-hub
+    #   spacy
+    #   transformers
+transformers==4.48.3
+    # via kokoro
+triton==3.0.0
+    # via torch
+typer==0.15.1
+    # via
+    #   gradio
+    #   spacy
+    #   weasel
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   cloudpathlib
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   phonemizer-fork
+    #   pydantic
+    #   pydantic-core
+    #   referencing
+    #   rich
+    #   spaces
+    #   torch
+    #   typer
+    #   uvicorn
+tzdata==2025.1
+    # via pandas
+unidic-lite==1.0.8
+    # via misaki
+uritemplate==4.1.1
+    # via csvw
+urllib3==2.3.0
+    # via requests
+uvicorn==0.34.0
+    # via gradio
+wasabi==1.1.3
+    # via
+    #   spacy
+    #   thinc
+    #   weasel
+weasel==0.4.1
+    # via spacy
+websockets==14.2
+    # via gradio-client
+wrapt==1.17.2
+    # via smart-open

style.css

@@ -0,0 +1,11 @@
+h1 {
+  text-align: center;
+  display: block;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}