SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.13043 · 2021

AudioCLIP: Extending CLIP to Image, Text and Audio

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2106.13043.json · badge: /api/ran/2106.13043.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
iver56/audiomentations community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
decay_to_beta Ran
ran on a synthesized input
iver56/audiomentations/audiomentations/augmentations/add_color_noise.py
code served (permissive licence) · get_code("7c18d1f2fc8cc8c3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "decay": 3.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
find_audio_files Ran
ran on a synthesized input
iver56/audiomentations/audiomentations/core/utils.py
code served (permissive licence) · get_code("7e90b20c82fb03c4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
from pathlib import Path

# Create a temporary directory with some mock audio files
temp_dir = tempfile.mkdtemp()

# Create some test audio files
test_files = [
    os.path.join(temp_dir, "song1.mp3"),
    os.path.join(temp_dir, "song2.wav"),
    os.path.join(temp_dir, "document.txt"),
]

for file_path in test_files[:2]:
    Path(file_path).touch()

# Create a subdirectory with more audio files
subdir = os.path.join(temp_dir, "subdir")
os.makedirs(subdir, exist_ok=True)
sub_audio = os.path.join(subdir, "song3.flac")
Path(sub_audio).touch()

SUPPORTED_EXTENSIONS = ('.aac', '.aif', '.aiff', '.flac', '.m4a', '.mp3', '.mp4', '.ogg', '.opus', '.wav')

ARGS = {
    "root_path": temp_dir,
    "filename_endings": SUPPORTED_EXTENSIONS,
    "traverse_subdirectories": True,
    "follow_symlinks": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
find_audio_files_in_paths Ran
ran on a synthesized input
iver56/audiomentations/audiomentations/core/utils.py
code served (permissive licence) · get_code("7adfe52e0a0a847d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
from pathlib import Path

# Create a temporary directory structure with some audio files
with tempfile.TemporaryDirectory() as tmpdir:
    # Create some mock audio files
    audio_dir = Path(tmpdir) / "audio"
    audio_dir.mkdir()
    
    # Create some subdirectories with audio files
    subdir1 = audio_dir / "subdir1"
    subdir1.mkdir()
    subdir2 = audio_dir / "subdir2"
    subdir2.mkdir()
    
    # Create mock audio files (empty files with audio extensions)
    (audio_dir / "song1.mp3").touch()
    (audio_dir / "song2.wav").touch()
    (subdir1 / "song3.flac").touch()
    (subdir1 / "song4.m4a").touch()
    (subdir2 / "song5.aac").touch()
    (audio_dir / "readme.txt").touch()  # Non-audio file
    
    # Test with single path as string
    test_path_str = str(audio_dir)
    
    # Test with single path as Path object
    test_path_obj = audio_dir
    
    # Test with list of paths (mix of strings and Path objects)
    test_paths_list = [audio_dir / "song1.mp3", str(subdir1)]
    
    ARGS = {
        "paths": test_paths_list,
        "filename_endings": ('.mp3', '.wav', '.flac', '.m4a', '.aac'),
        "traverse_subdirectories": True,
        "follow_symlinks": True,
    }
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
format_args Ran
ran on a synthesized input
iver56/audiomentations/audiomentations/core/utils.py
code served (permissive licence) · get_code("7db07f5e74e6c524")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from typing import Any

torch.manual_seed(0)

# The function format_args takes a dict[str, Any] and formats it as a string
# It iterates through key-value pairs and formats strings with quotes, other values as str()

# Create a diverse dict with various types to test the function
args_dict = {
    "learning_rate": 0.001,
    "batch_size": 32,
    "model_name": "bert-base",
    "epochs": 10,
    "dropout": 0.5,
    "use_cuda": False,
    "layers": [128, 64, 32],
    "config": {"hidden_dim": 256, "num_heads": 8},
    "tensor": torch.randn(2, 4),
}

ARGS = {
    "args_dict": args_dict,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_shortest_class_fullname Ran
ran on a synthesized input
iver56/audiomentations/audiomentations/core/serialization.py
code served (permissive licence) · get_code("b07b270a65ccaba2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from typing import Any

# Create a simple test class to pass to get_shortest_class_fullname
class TestClass:
    pass

# Create a class that looks like it's from audiomentations module
class AudiomentationsTestClass:
    __module__ = 'audiomentations.core'
    __name__ = 'SomeTransform'

# Create a class with a single-part module name
class SimpleClass:
    __module__ = 'simple'
    __name__ = 'MyClass'

# Test with TestClass - it will have __main__ as module
ARGS = {
    'cls': TestClass
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
shorten_class_name Ran
ran on a synthesized input
iver56/audiomentations/audiomentations/core/serialization.py
code served (permissive licence) · get_code("7fee2825b85bfbe7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    "class_fullname": "audiomentations.transforms.AddGaussianNoise"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In the past, the rapidly evolving field of sound classification greatly benefited from the application of methods from other domains. Today, we observe the trend to fuse domain-specific tasks and approaches together, which provides the community with new outstanding models. In this work, we present an extension of the CLIP model that handles audio in addition to text and images. Our proposed model incorporates the ESResNeXt audio-model into the CLIP framework using the AudioSet dataset. Such a combination enables the proposed model to perform bimodal and unimodal classification and querying, while keeping CLIP's ability to generalize to unseen datasets in a zero-shot inference fashion. AudioCLIP achieves new state-of-the-art results in the Environmental Sound Classification (ESC) task, out-performing other approaches by reaching accuracies of 90.07% on the UrbanSound8K and 97.15% on the ESC-50 datasets. Further it sets new baselines in the zero-shot ESC-task on the same datasets (68.78% and 69.40%, respectively). Finally, we also assess the cross-modal querying performance of the proposed model as well as the influence of full and partial training on the results. For the sake of reproducibility, our code is published.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.13043")
get_code_for_paper("2106.13043")
have("2106.13043")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.13043.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.13043.svg)](https://syntology.ai/paper/2106.13043)

Connect an agent — have() is free.