SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.03183 · 2023

Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 12 failures of our instrument; 2 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/2307.03183.json · badge: /api/ran/2307.03183.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
YuanGongND/whisper-at canonical (classifier label)
classifier basis: census
15 ran · 2 no recorded run
FunctionStatusWhere it lives
calculate_stats Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YuanGongND/whisper-at/src/whisper_at_train/utilities/stats.py
code served (permissive licence) · get_code("d358725a8a4995c9")
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 numpy as np

np.random.seed(0)

# Create small sample data: 5 samples, 3 classes
samples_num = 5
classes_num = 3

# output: 2d array of shape (samples_num, classes_num) with scores/probabilities
output = np.random.rand(samples_num, classes_num).astype(np.float32)

# target: 2d array of shape (samples_num, classes_num) with one-hot encoded labels
target = np.zeros((samples_num, classes_num), dtype=np.int32)
# Assign one class per sample (one-hot)
for i in range(samples_num):
    target[i, i % classes_num] = 1

ARGS = {
    'output': output,
    'target': target,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn — 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
computeMatchmap Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/utilities/util.py
code served (permissive licence) · get_code("5ee11f4af0d2fc1e")
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 Tensor, ndim 3, dtype family float, shape (3, 5, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# I should be a 3D tensor with shape (D, H, W)
# A should be a 2D tensor with shape (D, T)
# The function reshapes I to (H*W, D), transposes to (H*W, D),
# then multiplies with A (D, T) to get (H*W, T), then reshapes to (H, W, T)

D = 4  # feature dimension
H = 3  # height
W = 5  # width
T = 2  # output channels

I = torch.randn(D, H, W)
A = torch.randn(D, T)

ARGS = {
    "I": I,
    "A": A
}
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 Tensor, ndim 3, dtype family float, shape (3, 5, 2) — shape (3, 5, 2) as a later run recorded it
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
d_prime Ran
ran, honoured the contract we drafted
YuanGongND/whisper-at/src/whisper_at_train/utilities/stats.py
code served (permissive licence) · get_code("e469cef4384ff73a")
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
from scipy import stats

torch_seed = 0

ARGS = {
    "auc": 0.75
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
fileList Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/noise_robust_asr/asr_experiments/transcribe_whisper.py
code served (permissive licence) · get_code("638f8f1d05f173c7")
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
import shutil

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

# Create subdirectories and audio files
os.makedirs(os.path.join(temp_dir, "subdir1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "subdir2"), exist_ok=True)

# Create dummy audio files
open(os.path.join(temp_dir, "audio1.flac"), "w").close()
open(os.path.join(temp_dir, "audio2.wav"), "w").close()
open(os.path.join(temp_dir, "subdir1", "audio3.flac"), "w").close()
open(os.path.join(temp_dir, "subdir2", "audio4.wav"), "w").close()
open(os.path.join(temp_dir, "other.txt"), "w").close()  # Should be ignored

ARGS = {
    "source": temp_dir
}
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
get_feat_shape Ran
ran, honoured the contract we drafted
YuanGongND/whisper-at/src/whisper_at_train/utilities/compute_flops.py
code served (permissive licence) · get_code("e3a904304feac15a")
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 tuple, ndim 1, dtype family int; 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 torch

torch.manual_seed(0)

ARGS = {
    'mdl_size': 'tiny.en'
}
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 tuple, ndim 1, dtype family int — a tuple 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
get_immediate_files Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/noise_robust_asr/asr_experiments/transcribe_whisper.py
code served (permissive licence) · get_code("64ddb5ad0af650e6")
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

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

# Create some test files in the temporary directory
test_files = ['file1.txt', 'file2.py', 'file3.md']
for filename in test_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write('test content')

# Also create a subdirectory (which should not be included)
subdir = os.path.join(temp_dir, 'subdir')
os.makedirs(subdir)

ARGS = {
    'a_dir': temp_dir
}
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
get_immediate_files_with_extension Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/utilities/rename_state_dict.py
code served (permissive licence) · get_code("2bb7da1cdb95b512")
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

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

# Create some .pth files
open(os.path.join(temp_dir, 'model1.pth'), 'w').close()
open(os.path.join(temp_dir, 'model2.pth'), 'w').close()
open(os.path.join(temp_dir, 'data.txt'), 'w').close()
open(os.path.join(temp_dir, 'config.json'), 'w').close()

# Create a subdirectory (should not be included)
subdir = os.path.join(temp_dir, 'subdir')
os.makedirs(subdir, exist_ok=True)
open(os.path.join(subdir, 'model3.pth'), 'w').close()

ARGS = {
    'directory': temp_dir,
    'extension': 'pth'
}
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
lookup_list Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/dataloader_feat.py
code served (permissive licence) · get_code("c15efdd12442aeb4")
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 tempfile
import csv
import os

# Create a temporary CSV file with the required structure
temp_dir = tempfile.mkdtemp()
label_csv_path = os.path.join(temp_dir, "labels.csv")

# Write a sample CSV file with 'index' and 'display_name' columns
with open(label_csv_path, 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['index', 'display_name'])
    writer.writeheader()
    writer.writerow({'index': '0', 'display_name': 'cat'})
    writer.writerow({'index': '1', 'display_name': 'dog'})
    writer.writerow({'index': '2', 'display_name': 'bird'})

# Define the arguments
ARGS = {
    'index_list': ['0', '1', '2'],
    'label_csv': label_csv_path
}
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
make_index_dict Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/dataloader_feat.py
code served (permissive licence) · get_code("a8fb3f62e2a901d7")
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 dict. 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 csv
import tempfile
import os

# Create a temporary CSV file with the expected structure
temp_dir = tempfile.mkdtemp()
label_csv_path = os.path.join(temp_dir, "labels.csv")

# Write a sample CSV file with 'mid' and 'index' columns
with open(label_csv_path, 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['mid', 'index'])
    writer.writeheader()
    writer.writerow({'mid': 'mid_001', 'index': '0'})
    writer.writerow({'mid': 'mid_002', 'index': '1'})
    writer.writerow({'mid': 'mid_003', 'index': '2'})

ARGS = {
    'label_csv': label_csv_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
make_index_dict Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/gen_weight_file.py
code served (permissive licence) · get_code("ad2738e74fab6072")
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 dict. 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 sys, os, csv
import tempfile

# Create a temporary CSV file with the expected format
temp_dir = tempfile.mkdtemp()
label_csv_path = os.path.join(temp_dir, 'labels.csv')

# Write a sample CSV file with 'mid' and 'index' columns
with open(label_csv_path, 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['mid', 'index'])
    writer.writeheader()
    writer.writerow({'mid': 'entity_001', 'index': '0'})
    writer.writerow({'mid': 'entity_002', 'index': '1'})
    writer.writerow({'mid': 'entity_003', 'index': '2'})

ARGS = {
    'label_csv': label_csv_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
make_name_dict Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/dataloader_feat.py
code served (permissive licence) · get_code("cbf115a314bcd23e")
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 dict. 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 csv
import tempfile
import os

# Create a temporary CSV file with the expected structure
temp_dir = tempfile.mkdtemp()
label_csv_path = os.path.join(temp_dir, "labels.csv")

with open(label_csv_path, 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['index', 'display_name'])
    writer.writeheader()
    writer.writerow({'index': '0', 'display_name': 'cat'})
    writer.writerow({'index': '1', 'display_name': 'dog'})
    writer.writerow({'index': '2', 'display_name': 'bird'})

ARGS = {
    'label_csv': label_csv_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
matchmapSim Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/utilities/util.py
code served (permissive licence) · get_code("546678fcbd2854db")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create a 3D tensor: (batch=2, height=3, width=4)
# The function calls .max(0), .max(2), and .mean() on it
M = torch.randn(2, 3, 4)

# simtype can be one of: 'SISA', 'MISA', or 'SIMA'
simtype = 'SISA'

ARGS = {
    'M': M,
    'simtype': simtype
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
show_twod Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/noise_robust_asr/asr_experiments/transcribe_whisper.py
code served (permissive licence) · get_code("2f2ef8ef8d2e3a68")
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

torch.manual_seed(0)

ARGS = {
    'input': 3.14159
}
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
sinusoids Ran
ran, honoured the contract we drafted
YuanGongND/whisper-at/package/whisper-at/whisper_at/model.py
code served (permissive licence) · get_code("e529c9641c178fe0")
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 Tensor, ndim 2, dtype family float, shape (8, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import torch

torch.manual_seed(0)

ARGS = {
    "length": 8,
    "channels": 4,
    "max_timescale": 10000,
}
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 Tensor, ndim 2, dtype family float, shape (8, 4) — shape (8, 4) as a later run recorded it
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
trunc_normal_ Ran
ran; our contract draft was wrong, not the code
YuanGongND/whisper-at/src/whisper_at_train/models.py
code served (permissive licence) · get_code("56444fdea1ddc18d")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 math

torch.manual_seed(0)

# Create a small tensor to be initialized
tensor = torch.empty(2, 4)

# Define arguments for trunc_normal_
ARGS = {
    "tensor": tensor,
    "mean": 0.0,
    "std": 1.0,
    "a": -2.0,
    "b": 2.0,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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
calc_recalls Not yet run
unverified (harvested, no recorded run)
YuanGongND/whisper-at/src/whisper_at_train/utilities/util.py
code served (permissive licence) · get_code("0bed13389f791924")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
YuanGongND/whisper-at/src/whisper_at_train/traintest.py
code served (permissive licence) · get_code("7d2dd5f84e2a6da3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 9 later) and 7 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.

FunctionAlso present inEarliest-datedOthers named
trunc_normal_ 160 other papers
62 dated earlier, 3 the same month, 93 later, 2 same year, order not determinable · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
sinusoids 9 other papers
2 dated earlier, 7 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2306.05284 (2023-06)
Simple and Controllable Music Generation
2308.06112 (2023-08)
Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
and 6 more not named here
lookup_list 7 other papers
2 dated earlier, 5 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
2402.04882 (2024-02)
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
and 4 more not named here
make_index_dict 7 other papers
2 dated earlier, 5 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
2402.04882 (2024-02)
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
and 4 more not named here
make_name_dict 7 other papers
2 dated earlier, 5 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
2402.04882 (2024-02)
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
and 4 more not named here
d_prime 4 other papers
2 dated earlier, 2 later
1903.00765 (2019-03)
Weakly Labelled AudioSet Tagging with Attention Neural Networks
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2402.04882 (2024-02)
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
and 1 more not named here
calc_recalls 2 other papers
1 dated earlier, 1 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2402.04882 (2024-02)
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
computeMatchmap 2 other papers
1 dated earlier, 1 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2402.04882 (2024-02)
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
matchmapSim 2 other papers
1 dated earlier, 1 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2402.04882 (2024-02)
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units

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 this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whisper, and training a lightweight audio tagging model on top of it. With <1% extra computational cost, Whisper-AT can recognize audio events, in addition to spoken text, in a single forward pass.

For agents

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

get_harvested_code_for_paper("2307.03183")
get_code_for_paper("2307.03183")
have("2307.03183")

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

curl https://syntology.ai/api/ran/2307.03183.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.03183.svg)](https://syntology.ai/paper/2307.03183)

Connect an agent — have() is free.