initial commit

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,164 @@
+# 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
+
+# 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/
+.vscode/
+.ruff_cache/

README.md

@@ -0,0 +1,14 @@
+---
+title: Audiobox Aesthetics
+emoji: 📚
+colorFrom: purple
+colorTo: red
+sdk: gradio
+sdk_version: 5.16.0
+app_file: app.py
+pinned: false
+license: cc-by-4.0
+short_description: Demo for audiobox-aesthetics
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,134 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+# This file is copied & modified from UNESCO/MMS/blob/main/asr.py
+
+import gradio as gr
+import numpy as np
+import torch
+import torchaudio
+import json
+from audiobox_aesthetics import infer as aes_infer
+import plotly.graph_objects as go
+
+ASR_EXAMPLES = [("assets/bach.wav")]
+
+aes_predictor = aes_infer.initialize_model(None)
+
+
+def transcribe(audio_data=None):
+    if not audio_data:
+        return "<<ERROR: Empty Audio Input>>"
+
+    if isinstance(audio_data, tuple):
+        # microphone
+        sr, audio_samples = audio_data
+        audio_samples = (audio_samples / 32768.0).astype(np.float32)
+        audio_samples = torch.tensor(audio_samples)
+        if audio_samples.ndim == 1:
+            audio_samples = audio_samples[:, None]
+
+        assert audio_samples.ndim == 2
+        audio_samples = audio_samples.t()
+    else:
+        # file upload
+        if not isinstance(audio_data, str):
+            return "<<ERROR: Invalid Audio Input Instance: {}>>".format(
+                type(audio_data)
+            )
+        audio_samples, sr = torchaudio.load(audio_data)
+
+    transcription = json.loads(
+        aes_predictor.forward([{"path": audio_samples, "sample_rate": sr}])[0]
+    )
+
+    # reorder like paper figures
+    transcription = {
+        "Production Quality": transcription["PQ"],
+        "Production Complexity": transcription["PC"],
+        "Content Enjoyment": transcription["CE"],
+        "Content Usefulness": transcription["CU"],
+    }
+
+    # Create a Plotly bar plot
+    fig = go.Figure()
+    colors = ["#b1d8ff", "#fee2f5", "#cefac4", "#d2d3ff"]
+    values = list(transcription.values())
+    keys = list(transcription.keys())
+
+    fig.add_trace(
+        go.Bar(
+            x=keys,
+            y=values,
+            text=[f"{v:.2f}" for v in values],  # Format text to 2 decimal places
+            textposition="outside",  # Position text outside the bars
+            marker=dict(color=colors),
+        )
+    )
+
+    # Set the range for the y-axis
+    fig.update_layout(
+        yaxis=dict(range=[0, 10]),
+        xaxis_title="Metrics",
+        yaxis_title="Scores",
+    )
+    return fig
+
+
+main_interface = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.Audio(),
+    ],
+    # outputs="text",
+    outputs=gr.Plot(),
+    examples=ASR_EXAMPLES,
+    title="Audiobox Aesthetics Demo Prediction",
+    description=("Play some audio through microphone or upload the file."),
+    article="",
+    allow_flagging="never",
+)
+
+disclaimer = """
+## Disclaimer
+"""
+
+with gr.Blocks() as demo:
+    gr.HTML(
+        """
+            <div style="text-align: center;">
+            <h1>
+                Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
+            </h1>
+            </div>
+           """
+    )
+
+    gr.Markdown(
+        "<p align='center' style='font-size: 20px;'>See our <a href='https://arxiv.org/abs/2502.05139'>paper</a>, Github <a href='https://github.com/facebookresearch/audiobox-aesthetics'>repo</a> and HuggingFace <a href='https://huggingface.co/facebook/audiobox-aesthetics'>repo</a> </p>"
+    )
+    gr.HTML(
+        """<center><a href="https://huggingface.co/spaces/facebook/audiobox-aesthetics?duplicate=true"  style="display: inline-block;margin-top: .5em;margin-right: .25em;" target="_blank"><img style="margin-bottom: 0em;display: inline;margin-top: -.25em;" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a> for more control and no queue.</center>"""
+    )
+
+    main_interface.render()
+
+    gr.HTML(
+        """
+            <div class="footer" style="text-align:center">
+                <p>
+                    Model by <a href="https://ai.facebook.com" style="text-decoration: underline;" target="_blank">Meta AI</a> - Gradio Demo by 🤗 Hugging Face
+                </p>
+            </div>
+           """
+    )
+
+    # with gr.Row():
+    #     gr.Markdown(disclaimer)
+
+if __name__ == "__main__":
+    demo.queue()
+    demo.launch()

assets/bach.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bff9b5066c65e8b983d454f749559122a3039b42c513f8ed565cd9a6433402
+size 1769550

requirements.txt

@@ -0,0 +1,7 @@
+pip>=23.2
+gradio==5.16.0
+torch>=2.2.0
+torchaudio
+tqdm
+audiobox_aesthetics>=0.0.2
+plotly==6.0.0