Sync to HuggingFace Spaces

.gitattributes

@@ -0,0 +1,3 @@
+# Auto detect text files and perform LF normalization
+* text=auto
+*.ttf filter=lfs diff=lfs merge=lfs -text

.github/workflows/sync.yml

@@ -0,0 +1,27 @@
+name: Sync to Hugging Face Spaces
+
+on:
+    push:
+        branches:
+            - main
+
+jobs:
+    sync:
+        name: Sync
+        runs-on: ubuntu-latest
+
+        steps:
+            - name: Checkout Repository
+              uses: actions/checkout@v4
+              with:
+                  lfs: true
+
+            - run: rm -rf images
+
+            - name: Sync to Hugging Face Spaces
+              uses: JacobLinCool/huggingface-sync@v1
+              with:
+                  github: ${{ secrets.GITHUB_TOKEN }}
+                  user: jacoblincool # Hugging Face username or organization name
+                  space: audio-vis # Hugging Face space name
+                  token: ${{ secrets.HF_TOKEN }} # Hugging Face token

.gitignore

@@ -0,0 +1,152 @@
+# 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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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 maintainted 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/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 JacobLinCool
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,36 @@
+---
+title: audio vis
+emoji: 🦄
+colorFrom: indigo
+colorTo: pink
+sdk: gradio
+short_description: Visualizing Audio Features.
+---
+
+# audio-vis
+
+Visualizing Audio Features.
+
+<a href="https://huggingface.co/spaces/jacoblincool/audio-vis" target="_blank">
+    <picture>
+        <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md-dark.svg">
+        <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md.svg">
+    </picture>
+</a>
+
+## Setup
+
+```sh
+micromamba create -n audio-vis python==3.12 librosa matplotlib numpy scipy pillow gradio -c conda-forge
+```
+
+## Run
+
+```sh
+micromamba activate audio-vis
+python app.py
+```
+
+## Screenshot
+
+![Screenshot](./images/audio-vis.png)

app.py

@@ -0,0 +1,3 @@
+from ui import app
+
+app.queue(status_update_rate=5.0, max_size=10).launch()

fonts/NotoSansTC-Regular.ttf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b137e2eb57a2d1e4cf391c886ab1b783a0e5ddb5c75254748bde00c15cb8ff5
+size 7110560

fonts/OFL.txt

@@ -0,0 +1,93 @@
+Copyright 2014-2021 Adobe (http://www.adobe.com/), with Reserved Font Name 'Source'
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded, 
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

gen.py

@@ -0,0 +1,195 @@
+import io
+import os
+import librosa
+import librosa.display
+import numpy as np
+import matplotlib
+from matplotlib.font_manager import fontManager
+import matplotlib.pyplot as plt
+from scipy.signal import butter, lfilter
+from PIL import Image
+
+FILTER_UPPER_BOUND = 20000
+FILTER_LOWER_BOUND = 0
+
+# use ./fonts/NotoSansTC-Regular.ttf
+fontManager.addfont("fonts/NotoSansTC-Regular.ttf")
+matplotlib.rc("font", family="Noto Sans TC")
+
+
+def butter_filter(data: np.ndarray, cutoff: int, fs: int, btype: str, order=5):
+    nyquist = 0.5 * fs
+    if btype in ["low", "high"]:
+        normal_cutoff = cutoff / nyquist
+    else:  # 'band'
+        normal_cutoff = [c / nyquist for c in cutoff]
+    b, a = butter(order, normal_cutoff, btype=btype, analog=False)
+    y = lfilter(b, a, data)
+    return y
+
+
+def plt_to_numpy(plt: plt.Figure) -> np.ndarray:
+    buf = io.BytesIO()
+    plt.savefig(buf, format="png")
+    buf.seek(0)
+    return np.array(Image.open(buf))
+
+
+def apply_filters(
+    y: np.ndarray,
+    sr: int,
+    highpass_cutoff: int,
+    lowpass_cutoff: int,
+    bandpass_low: int,
+    bandpass_high: int,
+):
+    if highpass_cutoff > FILTER_LOWER_BOUND:
+        y = butter_filter(y, highpass_cutoff, sr, "high")
+    if lowpass_cutoff > FILTER_LOWER_BOUND and lowpass_cutoff < sr / 2:
+        y = butter_filter(y, lowpass_cutoff, sr, "low")
+    if bandpass_low > FILTER_LOWER_BOUND and bandpass_high < sr / 2:
+        y = butter_filter(y, [bandpass_low, bandpass_high], sr, "band")
+    return y
+
+
+def analyze_audio(
+    file: str,
+    highpass_cutoff: int,
+    lowpass_cutoff: int,
+    bandpass_low: int,
+    bandpass_high: int,
+):
+    filename = os.path.basename(file)
+    y, sr = librosa.load(file)
+    y = apply_filters(
+        y, sr, highpass_cutoff, lowpass_cutoff, bandpass_low, bandpass_high
+    )
+
+    def plot_waveform(y: np.ndarray, sr: int) -> np.ndarray:
+        plt.figure(figsize=(14, 5))
+        librosa.display.waveshow(y, sr=sr)
+        plt.title(f"Waveform ({filename})")
+        plt.xlabel("Time")
+        plt.ylabel("Amplitude")
+        return plt_to_numpy(plt)
+
+    def plot_spectrogram(y: np.ndarray, sr: int) -> np.ndarray:
+        plt.figure(figsize=(14, 5))
+        D = librosa.amplitude_to_db(np.abs(librosa.stft(y)), ref=np.max)
+        librosa.display.specshow(D, sr=sr, x_axis="time", y_axis="log")
+        plt.colorbar(format="%+2.0f dB")
+        plt.title(f"Spectrogram ({filename})")
+        return plt_to_numpy(plt)
+
+    def plot_mfcc(y: np.ndarray, sr: int) -> np.ndarray:
+        mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
+        plt.figure(figsize=(14, 5))
+        librosa.display.specshow(mfccs, sr=sr, x_axis="time")
+        plt.colorbar()
+        plt.title(f"MFCC ({filename})")
+        return plt_to_numpy(plt)
+
+    def plot_zcr(y: np.ndarray) -> np.ndarray:
+        zcr = librosa.feature.zero_crossing_rate(y=y)
+        plt.figure(figsize=(14, 5))
+        plt.plot(zcr[0])
+        plt.title(f"Zero Crossing Rate ({filename})")
+        plt.xlabel("Frames")
+        plt.ylabel("Rate")
+        return plt_to_numpy(plt)
+
+    def plot_spectral_centroid(y: np.ndarray, sr: int) -> np.ndarray:
+        spectral_centroids = librosa.feature.spectral_centroid(y=y, sr=sr)[0]
+        frames = range(len(spectral_centroids))
+        t = librosa.frames_to_time(frames)
+        plt.figure(figsize=(14, 5))
+        plt.semilogy(t, spectral_centroids, label="Spectral centroid")
+        plt.title(f"Spectral Centroid ({filename})")
+        plt.xlabel("Time")
+        plt.ylabel("Hz")
+        return plt_to_numpy(plt)
+
+    def plot_spectral_bandwidth(y: np.ndarray, sr: int) -> np.ndarray:
+        spectral_bandwidth = librosa.feature.spectral_bandwidth(y=y, sr=sr)[0]
+        frames = range(len(spectral_bandwidth))
+        t = librosa.frames_to_time(frames)
+        plt.figure(figsize=(14, 5))
+        plt.semilogy(t, spectral_bandwidth, label="Spectral bandwidth")
+        plt.title(f"Spectral Bandwidth ({filename})")
+        plt.xlabel("Time")
+        plt.ylabel("Hz")
+        return plt_to_numpy(plt)
+
+    def plot_rms(y: np.ndarray) -> np.ndarray:
+        rms = librosa.feature.rms(y=y)[0]
+        plt.figure(figsize=(14, 5))
+        plt.plot(rms)
+        plt.title(f"RMS Energy ({filename})")
+        plt.xlabel("Frames")
+        plt.ylabel("RMS")
+        return plt_to_numpy(plt)
+
+    def plot_spectral_contrast(y: np.ndarray, sr: int) -> np.ndarray:
+        spectral_contrast = librosa.feature.spectral_contrast(y=y, sr=sr)
+        plt.figure(figsize=(14, 5))
+        librosa.display.specshow(spectral_contrast, sr=sr, x_axis="time")
+        plt.colorbar()
+        plt.title(f"Spectral Contrast ({filename})")
+        return plt_to_numpy(plt)
+
+    def plot_spectral_rolloff(y: np.ndarray, sr: int) -> np.ndarray:
+        spectral_rolloff = librosa.feature.spectral_rolloff(y=y, sr=sr)[0]
+        frames = range(len(spectral_rolloff))
+        t = librosa.frames_to_time(frames)
+        plt.figure(figsize=(14, 5))
+        plt.semilogy(t, spectral_rolloff, label="Spectral rolloff")
+        plt.xlabel("Time")
+        plt.ylabel("Hz")
+        plt.title(f"Spectral Rolloff ({filename})")
+        return plt_to_numpy(plt)
+
+    def plot_tempo(onset_env: np.ndarray, sr: int) -> np.ndarray:
+        dtempo = librosa.feature.tempo(onset_envelope=onset_env, sr=sr, aggregate=None)
+        frames = range(len(dtempo))
+        t = librosa.frames_to_time(frames, sr=sr)
+        plt.figure(figsize=(14, 5))
+        plt.plot(t, dtempo, label="Tempo")
+        plt.title(f"Tempo ({filename})")
+        plt.xlabel("Time")
+        plt.ylabel("Tempo")
+        return plt_to_numpy(plt)
+
+    def plot_tempogram(onset_env: np.ndarray, sr: int) -> np.ndarray:
+        tempogram = librosa.feature.tempogram(onset_envelope=onset_env, sr=sr)
+        plt.figure(figsize=(14, 5))
+        librosa.display.specshow(tempogram, sr=sr, x_axis="time")
+        plt.colorbar()
+        plt.title(f"Tempogram ({filename})")
+        return plt_to_numpy(plt)
+
+    waveform = plot_waveform(y, sr)
+    spectrogram = plot_spectrogram(y, sr)
+    mfcc = plot_mfcc(y, sr)
+    zcr = plot_zcr(y)
+    spectral_centroid = plot_spectral_centroid(y, sr)
+    spectral_bandwidth = plot_spectral_bandwidth(y, sr)
+    rms = plot_rms(y)
+    spectral_contrast = plot_spectral_contrast(y, sr)
+    spectral_rolloff = plot_spectral_rolloff(y, sr)
+    onset_env = librosa.onset.onset_strength(y=y, sr=sr)
+    tempo = plot_tempo(onset_env, sr)
+    tempogram = plot_tempogram(onset_env, sr)
+
+    return (
+        waveform,
+        spectrogram,
+        mfcc,
+        zcr,
+        spectral_centroid,
+        spectral_bandwidth,
+        rms,
+        spectral_contrast,
+        spectral_rolloff,
+        tempo,
+        tempogram,
+    )

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+librosa
+matplotlib
+numpy
+scipy
+pillow

ui.py

@@ -0,0 +1,119 @@
+import gradio as gr
+from gen import FILTER_LOWER_BOUND, FILTER_UPPER_BOUND, analyze_audio
+
+with gr.Blocks() as app:
+    gr.Markdown(
+        """
+        # Audio Feature Visualization
+        
+        Upload an audio file to visualize its features and optionally apply filters. Each visualization helps in understanding different aspects of the audio signal.
+        """
+    )
+
+    with gr.Row():
+        audio = gr.Audio(
+            sources=["upload", "microphone"],
+            type="filepath",
+            label="Audio File",
+        )
+
+    with gr.Row():
+        highpass = gr.Slider(
+            FILTER_LOWER_BOUND - 1,
+            FILTER_UPPER_BOUND,
+            step=1,
+            label="High-pass filter cutoff frequency (Hz).",
+            info="Frequency above which signals are allowed to pass through.",
+            value=FILTER_LOWER_BOUND - 1,
+        )
+
+        lowpass = gr.Slider(
+            FILTER_LOWER_BOUND - 1,
+            FILTER_UPPER_BOUND,
+            step=1,
+            label="Low-pass filter cutoff frequency (Hz).",
+            info="Frequency below which signals are allowed to pass through.",
+            value=FILTER_LOWER_BOUND - 1,
+        )
+
+    with gr.Row():
+        bandpass_low = gr.Slider(
+            FILTER_LOWER_BOUND - 1,
+            FILTER_UPPER_BOUND,
+            step=1,
+            label="Band-pass filter low cutoff frequency (Hz).",
+            info="Lower frequency bound for band-pass filter.",
+            value=FILTER_LOWER_BOUND - 1,
+        )
+
+        bandpass_high = gr.Slider(
+            FILTER_LOWER_BOUND - 1,
+            FILTER_UPPER_BOUND,
+            step=1,
+            label="Band-pass filter high cutoff frequency (Hz).",
+            info="Higher frequency bound for band-pass filter.",
+            value=FILTER_LOWER_BOUND - 1,
+        )
+
+    btn = gr.Button("Visualize Features", variant="primary")
+
+    with gr.Row():
+        waveform = gr.Image(
+            label="Waveform: Visual representation of the audio signal over time."
+        )
+
+    with gr.Row():
+        spectrogram = gr.Image(
+            label="Spectrogram: Graphical representation of the spectrum of frequencies in a sound signal as they vary with time."
+        )
+        mfcc = gr.Image(
+            label="MFCC: Mel-frequency cepstral coefficients, representing the short-term power spectrum of a sound."
+        )
+
+    with gr.Row():
+        rms_energy = gr.Image(
+            label="RMS Energy: Root Mean Square energy of the audio signal."
+        )
+        zero_crossing_rate = gr.Image(
+            label="Zero Crossing Rate: Rate at which the signal changes from positive to negative or back."
+        )
+
+    with gr.Row():
+        spectral_centroid = gr.Image(
+            label="Spectral Centroid: Indicates where the center of mass of the spectrum is located."
+        )
+        spectral_bandwidth = gr.Image(
+            label="Spectral Bandwidth: The width of a range of frequencies."
+        )
+
+    with gr.Row():
+        spectral_rolloff = gr.Image(
+            label="Spectral Rolloff: Frequency below which a specified percentage of the total spectral energy lies."
+        )
+        spectral_contrast = gr.Image(
+            label="Spectral Contrast: Difference in amplitude between peaks and valleys in a sound spectrum."
+        )
+
+    with gr.Row():
+        tempo = gr.Image(label="Tempo: Estimated tempo of the audio signal.")
+        tempogram = gr.Image(
+            label="Tempogram: Localized autocorrelation of the onset strength envelope."
+        )
+
+    btn.click(
+        fn=analyze_audio,
+        inputs=[audio, highpass, lowpass, bandpass_low, bandpass_high],
+        outputs=[
+            waveform,
+            spectrogram,
+            mfcc,
+            zero_crossing_rate,
+            spectral_centroid,
+            spectral_bandwidth,
+            rms_energy,
+            spectral_contrast,
+            spectral_rolloff,
+            tempo,
+            tempogram,
+        ],
+    )