Add initial project structure with FastAPI and audio generation functionality

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.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
+
+# 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.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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+# PyPI configuration file
+.pypirc

Dockerfile

@@ -0,0 +1,42 @@
+FROM python:3.8
+
+# Set a writable cache directory for Hugging Face models
+ENV HF_HOME="/tmp/huggingface_cache"
+ENV MPLCONFIGDIR="/tmp/matplotlib_cache"
+ENV TRANSFORMERS_CACHE="/tmp/huggingface"
+ENV NUMBA_CACHE_DIR="/tmp/numba_cache"
+
+# Create and set correct permissions for cache directories
+RUN mkdir -p $HF_HOME $MPLCONFIGDIR $TRANSFORMERS_CACHE $NUMBA_CACHE_DIR \
+    && chmod -R 777 $HF_HOME $MPLCONFIGDIR $TRANSFORMERS_CACHE $NUMBA_CACHE_DIR
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set up a non-root user to avoid permission issues
+RUN useradd -m appuser
+USER appuser
+
+# Set the PATH to include local bin directory
+ENV PATH="/home/appuser/.local/bin:$PATH"
+
+# Install Python dependencies
+COPY --chown=appuser:appuser requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Manually install uvicorn in case it failed above
+RUN pip install uvicorn
+
+# Verify that uvicorn was installed
+RUN pip show uvicorn
+
+# Copy the API code
+COPY --chown=appuser:appuser . .
+
+# Expose the port
+EXPOSE 5000
+
+# Run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "5000"]

app.py

@@ -0,0 +1,89 @@
+import os
+import gradio as gr
+import uvicorn
+
+from sound_generator import generate_sound, generate_music
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import FileResponse
+from pydantic import BaseModel
+
+# Create the FastAPI app
+app = FastAPI()
+
+
+# Configuración de CORS para permitir solicitudes desde cualquier origen
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=[
+        "*"
+    ],  # Permitir todos los orígenes (puedes restringirlo a tus orígenes específicos)
+    allow_credentials=True,
+    allow_methods=["*"],  # Permitir todos los métodos HTTP (GET, POST, OPTIONS, etc.)
+    allow_headers=["*"],  # Permitir todos los encabezados
+)
+
+
+# Define a Pydantic model to handle the input prompt
+class AudioRequest(BaseModel):
+    prompt: str
+
+
+@app.post("/generate-sound/")
+async def generate_sound_endpoint(request: AudioRequest):
+    try:
+        # Llamada a la función para generar el sonido
+        audio_file_path = generate_sound(request.prompt)
+
+        # Verifica si el archivo se ha generado correctamente
+        if not os.path.exists(audio_file_path):
+            raise HTTPException(
+                status_code=404, detail="Archivo de audio no encontrado."
+            )
+
+        # Regresar el archivo generado como una respuesta de descarga
+        return FileResponse(
+            audio_file_path, media_type="audio/wav", filename="generated_audio.wav"
+        )
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.post("/generate-music/")
+async def generate_music_endpoint(request: AudioRequest):
+    try:
+        # Call the synchronous generate_music function
+        audio_file_path = generate_music(request.prompt)
+
+        # Verifies if the file has been generated correctly
+        if not os.path.exists(audio_file_path):
+            raise HTTPException(
+                status_code=404, detail="Archivo de audio no encontrado."
+            )
+
+        # Return the generated file as a download response
+        return FileResponse(
+            audio_file_path, media_type="audio/wav", filename="generated_audio.wav"
+        )
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+# Crear interfaz de Gradio separadamente
+with gr.Blocks() as demo:
+    gr.Markdown("# API de Sonidos Generativos")
+    gr.Markdown("Bienvenido al servicio de generación de sonidos mediante IA.")
+    gr.Markdown(
+        "Esta API está disponible para uso a través de los siguientes endpoints:"
+    )
+    gr.Markdown("- Generar sonido: `/generate-sound/`")
+    gr.Markdown("- Generar música: `/generate-music/`")
+    gr.Markdown("- Documentación de la API: `/docs`")
+
+# Montar Gradio en FastAPI - IMPORTANTE: esto debe hacerse antes de iniciar el servidor
+app = gr.mount_gradio_app(app, demo, path="/")
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,10 @@
+scipy==1.9.3
+git+https://github.com/facebookresearch/audiocraft.git
+ffmpeg==1.4
+numpy==1.24.4
+spacy==3.7.6
+torch==2.1.0
+pydantic==2.1.1
+fastapi==0.115.11
+uvicorn==0.33.0
+gradio==5.20.1

sound_generator.py

@@ -0,0 +1,51 @@
+from audiocraft.models import AudioGen, MusicGen
+from audiocraft.data.audio import audio_write
+
+# Load the pretrained model (you can choose "small", "medium", or "large")
+sound_model = AudioGen.get_pretrained('facebook/audiogen-medium')
+music_model = MusicGen.get_pretrained('facebook/musicgen-small')
+
+# Set generation parameters (for example, audio duration of 8 seconds)
+sound_model.set_generation_params(duration=5)
+music_model.set_generation_params(duration=5)
+
+def generate_sound(prompt: str):
+    """
+    Generate sound using Audiocraft based on the given prompt.
+    
+    Args:
+    - prompt (str): The description of the sound/music to generate.
+    
+    Returns:
+    - str: The path to the saved audio file.
+    """
+    # Generate the audio for the provided prompt
+    descriptions = [prompt]  # We use the prompt as a description for the model
+    wav = sound_model.generate(descriptions)  # Generates 2 samples
+    
+    # Save the generated audio file with loudness normalization
+    output_path = 'generated_audio'
+    audio_write(output_path, wav[0].cpu(), sound_model.sample_rate, strategy="loudness")
+    
+    return f"{output_path}.wav"
+
+
+def generate_music(prompt: str):
+    """
+    Generate music using Audiocraft based on the given prompt.
+    
+    Args:
+    - prompt (str): The description of the music to generate.
+    
+    Returns:
+    - str: The path to the saved audio file.
+    """
+    # Generate the music for the provided prompt
+    descriptions = [prompt]  # We use the prompt as a description for the model
+    wav = music_model.generate(descriptions)  # Generates 2 samples
+    
+    # Save the generated audio file with loudness normalization
+    output_path = 'generated_audio'
+    audio_write(output_path, wav[0].cpu(), music_model.sample_rate, strategy="loudness")
+    
+    return f"{output_path}.wav"