Refactor: Consolidate Gradio UI and unify submit logic

.gitignore

@@ -0,0 +1,206 @@
+*.pt
+*.ckpt
+*.onnx
+t5_g2p_model/
+embeddings/
+checkpoints/
+
+val_images/
+val_audios/
+lightning_logs/
+lightning_logs_/
+train_images/
+train_audios/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.idea/
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+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
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# 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
+
+# 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.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.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/
+*.txt
+!requirements.txt
+*.log
+*.flac
+minio_config.yaml
+.history/*
+__pycache__/*
+train.log
+*.mp3
+*.tar.gz
+__pycache__/
+demo_examples/
+nohup.out
+test_results/*
+nohup.out
+text_audio_align/*
+remote/*
+MG2P/*
+audio_getter.py
+refiner_loss_debug/
+outputs/*
+!outputs/
+save_checkpoint.ipynb
+repos/*
+app_demo.py
+ui/components_demo.py
+data_sampler_demo.py
+pipeline_ace_step_demo.py
+
+.vs
+.gradio
+venv

README.md

@@ -4,8 +4,7 @@ emoji: 📈
 colorFrom: blue
 colorTo: purple
 sdk: gradio
-sdk_version: 4.44.1
-python_version: 3.8.9
+sdk_version: 5.29.1
 app_file: app.py
 pinned: false
 license: apache-2.0

app.py

@@ -39,7 +39,7 @@ def convert_to_wav(in_filename: str) -> str:
     logging.info(f"Converting '{in_filename}' to '{out_filename}'")
 
     _ = os.system(
-        f"ffmpeg -hide_banner -i '{in_filename}' -ar 16000 -ac 1 '{out_filename}' -y"
+        f"ffmpeg -hide_banner -i \"{in_filename}\" -ar 16000 -ac 1 \"{out_filename}\" -y"
     )
 
     return out_filename
@@ -55,67 +55,82 @@ def build_html_output(s: str, style: str = "result_item_success"):
     """
 
 
-def process_url(
+def submit_fn(
     repo_id: str,
-    url: str,
+    uploaded_file_path: str,
+    microphone_audio_path: str,
+    url_text: str,
 ):
-    logging.info(f"Processing URL: {url}")
-    with tempfile.NamedTemporaryFile() as f:
+    in_filename = None
+    source_description = ""
+
+    if uploaded_file_path:
+        in_filename = uploaded_file_path
+        source_description = "uploaded file"
+        logging.info(f"Processing {source_description}: {in_filename}")
+        if not os.path.exists(in_filename):
+             return "", [], build_html_output(
+                 f"Uploaded file not found: {in_filename}, "
+                 "Please first upload a file and then click "
+                 'the button "submit for recognition"',
+                 "result_item_error",
+             )
+
+    elif microphone_audio_path:
+        in_filename = microphone_audio_path
+        source_description = "microphone recording"
+        logging.info(f"Processing {source_description}: {in_filename}")
+        if not os.path.exists(in_filename):
+             return "", [], build_html_output(
+                 f"Microphone recording not found: {in_filename}, "
+                 "Please first click 'Record from microphone', speak, "
+                 "click 'Stop recording', and then "
+                 "click the button 'submit for recognition'",
+                 "result_item_error"
+             )
+
+    elif url_text and url_text.strip():
+        source_description = "URL"
+        logging.info(f"Processing {source_description}: {url_text}")
+        # Ensure a temporary file is created that persists until process() is done with it.
+        # Using delete=False and manual cleanup is safer here.
+        temp_file = None
         try:
-            urllib.request.urlretrieve(url, f.name)
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".tmpaudio") as f:
+                temp_file = f.name # Store the name for cleanup
+            urllib.request.urlretrieve(url_text, temp_file)
+            in_filename = temp_file
+            # Process the downloaded file
+            eventStr, events, html_info = process(repo_id=repo_id, in_filename=in_filename)
+            # Clean up the temporary file after processing
+            if temp_file and os.path.exists(temp_file):
+                os.unlink(temp_file)
+            return eventStr, events, html_info
+        except Exception as e:
+            logging.error(f"Error processing URL {url_text}: {e}", exc_info=True)
+            # Clean up the temporary file in case of error
+            if temp_file and os.path.exists(temp_file):
+                os.unlink(temp_file)
+            return "", [], build_html_output(f"Error processing URL: {str(e)}", "result_item_error")
+    else:
+        return "", [], build_html_output(
+            "Please provide an audio input via upload, microphone, or URL.",
+            "result_item_error",
+        )
 
+    # Common processing for file-based inputs (upload, mic)
+    if in_filename:
+        try:
             return process(
-                in_filename=f.name,
+                in_filename=in_filename,
                 repo_id=repo_id,
             )
         except Exception as e:
-            logging.info(str(e))
-            return "", build_html_output(str(e), "result_item_error")
-
-
-def process_uploaded_file(
-    repo_id: str,
-    in_filename: str,
-):
-    if in_filename is None or in_filename == "":
-        return "", build_html_output(
-            "Please first upload a file and then click "
-            'the button "submit for recognition"',
-            "result_item_error",
-        )
-
-    logging.info(f"Processing uploaded file: {in_filename}")
-    try:
-        return process(
-            in_filename=in_filename,
-            repo_id=repo_id,
-        )
-    except Exception as e:
-        logging.info(str(e))
-        return "", build_html_output(str(e), "result_item_error")
-
-
-def process_microphone(
-    repo_id: str,
-    in_filename: str,
-):
-    if in_filename is None or in_filename == "":
-        return "", build_html_output(
-            "Please first click 'Record from microphone', speak, "
-            "click 'Stop recording', and then "
-            "click the button 'submit for recognition'",
-            "result_item_error",
-        )
+            logging.error(f"Error processing {source_description} {in_filename}: {e}", exc_info=True)
+            return "", [], build_html_output(f"Error processing {source_description}: {str(e)}", "result_item_error")
 
-    logging.info(f"Processing microphone: {in_filename}")
-    try:
-        return process(
-            in_filename=in_filename,
-            repo_id=repo_id,
-        )
-    except Exception as e:
-        logging.info(str(e))
-        return "", build_html_output(str(e), "result_item_error")
+    # Should not be reached if logic is correct, but as a fallback:
+    return "", [], build_html_output("No valid input provided.", "result_item_error")
 
 
 def process(
@@ -136,9 +151,10 @@ def process(
     tagger = get_pretrained_model(repo_id)
 
     events = decode(tagger, filename)
-
+    
+    eventStr = ", ".join([e.name for e in events])
     events = [[e.name, f"{e.prob:.2f}"] for e in events]
-
+    
     date_time = now.strftime("%Y-%m-%d %H:%M:%S.%f")
     end = time.time()
 
@@ -164,7 +180,7 @@ def process(
     logging.info(info)
     logging.info(f"\nrepo_id: {repo_id}\nDetected events: {events}")
 
-    return events, build_html_output(info)
+    return eventStr, events, build_html_output(info)
 
 
 title = "# Audio tagging with [Next-gen Kaldi](https://github.com/k2-fsa) "
@@ -211,23 +227,6 @@ with demo:
                 type="filepath",
                 label="Upload from disk",
             )
-            upload_button = gr.Button("Submit for recognition")
-
-            upload_output = gr.Dataframe(headers=["Event", "Probability"])
-            uploaded_html_info = gr.HTML(label="Info")
-
-            gr.Examples(
-                examples=examples,
-                inputs=[
-                    model_dropdown,
-                    uploaded_file,
-                ],
-                outputs=[
-                    upload_output,
-                    uploaded_html_info,
-                ],
-                fn=process_uploaded_file,
-            )
 
         with gr.TabItem("Record from microphone"):
             microphone = gr.Audio(
@@ -236,23 +235,6 @@ with demo:
                 label="Record from microphone",
             )
 
-            record_button = gr.Button("Submit for recognition")
-            microphone_output = gr.Dataframe(headers=["Event", "Probability"])
-            recorded_html_info = gr.HTML(label="Info")
-
-            gr.Examples(
-                examples=examples,
-                inputs=[
-                    model_dropdown,
-                    microphone,
-                ],
-                outputs=[
-                    microphone_output,
-                    recorded_html_info,
-                ],
-                fn=process_microphone,
-            )
-
         with gr.TabItem("From URL"):
             url_textbox = gr.Textbox(
                 max_lines=1,
@@ -261,42 +243,41 @@ with demo:
                 interactive=True,
             )
 
-            url_button = gr.Button("Submit for recognition")
-            url_output = gr.Dataframe(headers=["Event", "Probability"])
-            url_html_info = gr.HTML(label="Info")
-
-        upload_button.click(
-            process_uploaded_file,
-            inputs=[
-                model_dropdown,
-                uploaded_file,
-            ],
-            outputs=[
-                upload_output,
-                uploaded_html_info,
-            ],
-        )
-
-        record_button.click(
-            process_microphone,
-            inputs=[
-                model_dropdown,
-                microphone,
-            ],
-            outputs=[
-                microphone_output,
-                recorded_html_info,
-            ],
-        )
+    submit_button = gr.Button("Submit for recognition", variant="primary")
+
+    output_string = gr.Textbox(label="Event (string)", show_label=True, show_copy_button=True)
+    output_dataframe = gr.Dataframe(headers=["Event", "Probability"], label="Detected Events")
+    output_html_info = gr.HTML(label="Processing Info")
+
+    gr.Examples(
+        examples=examples,
+        inputs=[
+            model_dropdown,
+            uploaded_file,
+        ],
+        outputs=[
+            output_string,
+            output_dataframe,
+            output_html_info,
+        ],
+        fn=submit_fn,
+    )
 
-        url_button.click(
-            process_url,
-            inputs=[
-                model_dropdown,
-                url_textbox,
-            ],
-            outputs=[url_output, url_html_info],
-        )
+    # Connect the submit button to the unified function
+    submit_button.click(
+        fn=submit_fn,
+        inputs=[
+            model_dropdown,
+            uploaded_file,
+            microphone,
+            url_textbox,
+        ],
+        outputs=[
+            output_string,
+            output_dataframe,
+            output_html_info,
+        ],
+    )
 
     gr.Markdown(description)
 
@@ -305,4 +286,4 @@ if __name__ == "__main__":
 
     logging.basicConfig(format=formatter, level=logging.INFO)
 
-    demo.launch()
+    demo.launch(inbrowser=True)

requirements.txt

@@ -3,3 +3,4 @@ numpy
 
 huggingface_hub
 sherpa-onnx>=1.9.21
+gradio

webui.bat

@@ -0,0 +1,162 @@
+@echo off
+
+:: The original source of the webui.bat file is stable-diffusion-webui
+:: Modified and enhanced by Gemini with features for venv management and requirements handling.
+
+:: --------- Configuration ---------
+set COMMANDLINE_ARGS=
+:: Define the name of the Launch application
+set APPLICATION_NAME=app.py
+:: Define the name of the virtual environment directory
+set VENV_NAME=venv
+:: Set to 1 to always attempt to update packages from requirements.txt on every launch
+set ALWAYS_UPDATE_REQS=0
+:: ---------------------------------
+
+
+:: Set PYTHON executable if not already defined
+if not defined PYTHON (set PYTHON=python)
+:: Set VENV_DIR using VENV_NAME if not already defined
+if not defined VENV_DIR (set "VENV_DIR=%~dp0%VENV_NAME%")
+
+mkdir tmp 2>NUL
+
+:: Check if Python is callable
+%PYTHON% -c "" >tmp/stdout.txt 2>tmp/stderr.txt
+if %ERRORLEVEL% == 0 goto :check_pip
+echo Couldn't launch python
+goto :show_stdout_stderr
+
+:check_pip
+:: Check if pip is available
+%PYTHON% -mpip --help >tmp/stdout.txt 2>tmp/stderr.txt
+if %ERRORLEVEL% == 0 goto :start_venv
+:: If pip is not available and PIP_INSTALLER_LOCATION is set, try to install pip
+if "%PIP_INSTALLER_LOCATION%" == "" goto :show_stdout_stderr
+%PYTHON% "%PIP_INSTALLER_LOCATION%" >tmp/stdout.txt 2>tmp/stderr.txt
+if %ERRORLEVEL% == 0 goto :start_venv
+echo Couldn't install pip
+goto :show_stdout_stderr
+
+:start_venv
+:: Skip venv creation/activation if VENV_DIR is explicitly set to "-"
+if ["%VENV_DIR%"] == ["-"] goto :skip_venv_entirely
+:: Skip venv creation/activation if SKIP_VENV is set to "1"
+if ["%SKIP_VENV%"] == ["1"] goto :skip_venv_entirely
+
+:: Check if the venv already exists by looking for Python.exe in its Scripts directory
+dir "%VENV_DIR%\Scripts\Python.exe" >tmp/stdout.txt 2>tmp/stderr.txt
+if %ERRORLEVEL% == 0 goto :activate_venv_and_maybe_update
+
+:: Venv does not exist, create it
+echo Virtual environment not found in "%VENV_DIR%". Creating a new one.
+for /f "delims=" %%i in ('CALL %PYTHON% -c "import sys; print(sys.executable)"') do set PYTHON_FULLNAME="%%i"
+echo Creating venv in directory %VENV_DIR% using python %PYTHON_FULLNAME%
+%PYTHON_FULLNAME% -m venv "%VENV_DIR%" >tmp/stdout.txt 2>tmp/stderr.txt
+if %ERRORLEVEL% NEQ 0 (
+    echo Unable to create venv in directory "%VENV_DIR%"
+    goto :show_stdout_stderr
+)
+echo Venv created.
+
+:: Install requirements for the first time if venv was just created
+:: This section handles the initial installation of packages from requirements.txt
+:: immediately after a new virtual environment is created.
+echo Checking for requirements.txt for initial setup in %~dp0
+if exist "%~dp0requirements.txt" (
+    echo Found requirements.txt, attempting to install for initial setup...
+    call "%VENV_DIR%\Scripts\activate.bat"
+    echo Installing packages from requirements.txt ^(initial setup^)...
+    "%VENV_DIR%\Scripts\python.exe" -m pip install -r "%~dp0requirements.txt"
+    if %ERRORLEVEL% NEQ 0 (
+        echo Failed to install requirements during initial setup. Please check the output above.
+        pause
+        goto :show_stdout_stderr_custom_pip_initial 
+    )
+    echo Initial requirements installed successfully.
+    call "%VENV_DIR%\Scripts\deactivate.bat"
+) else (
+    echo No requirements.txt found for initial setup, skipping package installation.
+)
+goto :activate_venv_and_maybe_update
+
+
+:activate_venv_and_maybe_update
+:: This label is reached if the venv exists or was just created.
+:: Set PYTHON to point to the venv's Python interpreter.
+set PYTHON="%VENV_DIR%\Scripts\Python.exe"
+echo Activating venv: %PYTHON%
+
+:: Always update requirements if ALWAYS_UPDATE_REQS is 1
+:: This section allows for updating packages from requirements.txt on every launch
+:: if the ALWAYS_UPDATE_REQS variable is set to 1.
+if defined ALWAYS_UPDATE_REQS (
+    if "%ALWAYS_UPDATE_REQS%"=="1" (
+        echo ALWAYS_UPDATE_REQS is enabled.
+        if exist "%~dp0requirements.txt" (
+            echo Attempting to update packages from requirements.txt...
+            REM No need to call activate.bat here again, PYTHON is already set to the venv's python
+            %PYTHON% -m pip install -r "%~dp0requirements.txt"
+            if %ERRORLEVEL% NEQ 0 (
+                echo Failed to update requirements. Please check the output above.
+                pause
+                goto :endofscript 
+            )
+            echo Requirements updated successfully.
+        ) else (
+            echo ALWAYS_UPDATE_REQS is enabled, but no requirements.txt found. Skipping update.
+        )
+    ) else (
+        echo ALWAYS_UPDATE_REQS is not enabled or not set to 1. Skipping routine update.
+    )
+)
+
+goto :launch
+
+:skip_venv_entirely
+:: This label is reached if venv usage is explicitly skipped.
+echo Skipping venv.
+goto :launch
+
+:launch
+:: Launch the main application
+echo Launching Web UI with arguments: %COMMANDLINE_ARGS% %*
+%PYTHON% %APPLICATION_NAME% %COMMANDLINE_ARGS% %*
+echo Launch finished.
+pause
+exit /b
+
+:show_stdout_stderr_custom_pip_initial
+:: Custom error handler for failures during the initial pip install process.
+echo.
+echo exit code ^(pip initial install^): %errorlevel%
+echo Errors during initial pip install. See output above.
+echo.
+echo Launch unsuccessful. Exiting.
+pause
+exit /b
+
+
+:show_stdout_stderr
+:: General error handler: displays stdout and stderr from the tmp directory.
+echo.
+echo exit code: %errorlevel%
+
+for /f %%i in ("tmp\stdout.txt") do set size=%%~zi
+if %size% equ 0 goto :show_stderr
+echo.
+echo stdout:
+type tmp\stdout.txt
+
+:show_stderr
+for /f %%i in ("tmp\stderr.txt") do set size=%%~zi
+if %size% equ 0 goto :endofscript
+echo.
+echo stderr:
+type tmp\stderr.txt
+
+:endofscript
+echo.
+echo Launch unsuccessful. Exiting.
+pause
+exit /b