Feature/gradio UI , Added Gradio Web UI with Dual-Speaker Support, Examples, and Stability Fixes

.gitignore

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[codz]
@@ -11,6 +12,30 @@ api/outputs/
 # C extensions
 *.so
 
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# Ignore model checkpoints and generated outputs
+pretrained_models/
+outputs/
+
+# C extensions
+*.so
+
 # Distribution / packaging
 .Python
 build/
@@ -32,8 +57,6 @@ share/python-wheels/
 MANIFEST
 
 # PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
 *.manifest
 *.spec
 
@@ -86,58 +109,28 @@ target/
 # IPython
 profile_default/
 ipython_config.py
-.claude/
-CLAUDE.md
+
 # pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
 # .python-version
 
 # pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
 #Pipfile.lock
 
-# UV
-#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#uv.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry / pdm / pixi
 #poetry.lock
-#poetry.toml
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
-#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
 #pdm.lock
-#pdm.toml
 .pdm-python
 .pdm-build/
-
-# pixi
-#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
-#pixi.lock
-#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
-#   in the .venv directory. It is recommended not to include this directory in version control.
 .pixi
 
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+# PEP 582
 __pypackages__/
 
-# Celery stuff
+# Celery
 celerybeat-schedule
 celerybeat.pid
 
-# SageMath parsed files
+# SageMath
 *.sage.py
 
 # Environments
@@ -150,64 +143,66 @@ ENV/
 env.bak/
 venv.bak/
 
-# Spyder project settings
+# IDE / Editor settings
 .spyderproject
 .spyproject
-
-# Rope project settings
 .ropeproject
+.idea/
+.vscode/
 
-# mkdocs documentation
+# mkdocs site
 /site
 
-# mypy
+# mypy / pyre / pytype caches
 .mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
 .pyre/
-
-# pytype static type analyzer
 .pytype/
 
 # Cython debug symbols
 cython_debug/
 
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-# Abstra
-# Abstra is an AI-powered process automation framework.
-# Ignore directories containing user credentials, local state, and settings.
-# Learn more at https://abstra.io/docs
-.abstra/
-
-# Visual Studio Code
-#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
-#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
-#  you could uncomment the following to ignore the entire vscode folder
-# .vscode/
-
-# Ruff stuff:
+# Misc
+.DS_Store
+Thumbs.db
 .ruff_cache/
-
-# PyPI configuration file
 .pypirc
-
-# Cursor
-#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
-#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
-#  refer to https://docs.cursor.com/context/ignore-files
 .cursorignore
 .cursorindexingignore
 
 # Marimo
 marimo/_static/
 marimo/_lsp/
 __marimo__/
+
+# Models & Checkpoints (explicitly again for clarity)
+*.safetensors
+*.bin
+*.ckpt
+*.onnx
+
+# Output / Generated Audio
+*.wav
+*.mp3
+*.ogg
+
+# Cache & Temporary Files
+cache/
+tmp/
+*.tmp
+*.bak
+*.npy
+*.npz
+
+# Hugging Face / Torch / Diffusers Cache
+~/.cache/
+huggingface/
+hf_cache/
+transformers_cache/
+torch_cache/
+diffusers_cache/
+
+# Environment / Secrets
+.env
+.env.*
+secrets.json
+credentials.json

CHANGELOG.md

@@ -0,0 +1,19 @@
+# Changelog
+
+All notable changes to this repository should be documented in this file.
+
+## [Unreleased] - feature/gradio-ui (2025-10-30)
+
+  - Accepts either a structured podcast JSON (recommended) or a manual utterance.
+  - Supports optional reference audio/text and dialect prompts.
+  - Improved, more descriptive labels and user guidance in the UI.
+
+Notes for upstream maintainers:
+
+### Added (2025-10-31)
+
+- Document non-verbal/paralinguistic token support (e.g., <|laughter|>, <|breathing|>, <|coughing|>) in the README and examples. These tokens can be inserted into input text to control paralinguistic events during generation.
+ - Added Gradio UI Single / Dual Speaker tabs. Dual Speaker supports uploading two reference audios/texts and a dialogue textarea where lines can be prefixed with `S1:` and `S2:` to indicate speaker turns.
+ - Added `example/gradio/README.md` with usage examples and guidance for formatting dialogue and reference audio usage.
+ - Added `example/gradio/smoke_test.py` — lightweight smoke test to validate UI input handling and optionally run a full inference when `--run` is supplied.
+ - Updated README to document Gradio UI usage and bracketed `[S1]/[S2]` dialog tag format; linked to `example/gradio/README.md` and smoke test.