SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.17864 · 2023

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 4 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/2310.17864.json · badge: /api/ran/2310.17864.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
pytorch/audio canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
eval_env Ran
ran, violated the contract we drafted
pytorch/audio/src/torchaudio/_internal/module_utils.py
code served (permissive licence) · get_code("25d33eba42f595af")
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 bool, 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 os

# Set up environment variables for testing
os.environ['TEST_VAR_TRUE'] = '1'
os.environ['TEST_VAR_FALSE'] = '0'
os.environ['TEST_VAR_NOT_SET'] = ''
if 'TEST_VAR_NOT_SET' in os.environ:
    del os.environ['TEST_VAR_NOT_SET']

ARGS = {
    'var': 'TEST_VAR_TRUE',
    'default': False
}
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 bool, 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
fail_with_message Ran
ran; our contract draft was wrong, not the code
pytorch/audio/src/torchaudio/_internal/module_utils.py
code served (permissive licence) · get_code("a62536e09f055a5f")
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 function. 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 torch.nn as nn
from functools import wraps

torch.manual_seed(0)

def fail_with_message(message):
    """Generate decorator to give users message about missing TorchAudio extension."""

    def decorator(func):

        @wraps(func)
        def wrapped(*args, **kwargs):
            raise RuntimeError(f'{func.__module__}.{func.__name__} {message}')
        return wrapped
    return decorator


# The function takes a single parameter: message (a string)
# The function body uses message in an f-string to construct a RuntimeError
# No complex objects needed - just a simple string

ARGS = {
    "message": "is not available. Please install torchaudio."
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
inverse_mel_scale Ran
ran; our contract draft was wrong, not the code
pytorch/audio/src/torchaudio/compliance/kaldi.py
code served (permissive licence) · get_code("cd99ee7d35201131")
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

torch.manual_seed(0)

# The function takes a mel_freq tensor and applies an inverse mel scale transformation
# It expects a tensor input and returns a tensor output
mel_freq = torch.randn(2, 4)

ARGS = {
    "mel_freq": mel_freq
}
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
inverse_mel_scale_scalar Ran
ran, honoured the contract we drafted
pytorch/audio/src/torchaudio/compliance/kaldi.py
code served (permissive licence) · get_code("0f943f916295a5a2")
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 float, 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 math

def inverse_mel_scale_scalar(mel_freq: float) -> float:
    return 700.0 * (math.exp(mel_freq / 1127.0) - 1.0)

ARGS = {
    "mel_freq": 2.5
}
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 float, 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
no_op Ran
ran; our contract draft was wrong, not the code
pytorch/audio/src/torchaudio/_internal/module_utils.py
code served (permissive licence) · get_code("cfa503d2d20f62b7")
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 function. 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 torch.nn as nn

torch.manual_seed(0)

# The no_op decorator takes a function as input and returns it unchanged
# So we need to provide a simple function as the argument

def simple_function():
    """A simple test function."""
    return 42

ARGS = {
    "func": simple_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
spectrogram Ran
ran; our contract draft was wrong, not the code
pytorch/audio/src/torchaudio/compliance/kaldi.py
code served (permissive licence) · get_code("4aab9a5564103eaf")
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 (98, 257) 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)

# Based on the function signature, I need to identify all parameters
# The function is `spectrogram` but the code shown is incomplete
# From the helper functions and context, I can infer the spectrogram function signature
# Let me construct arguments based on typical spectrogram function parameters

ARGS = {
    'waveform': torch.randn(2, 16000),  # 2 channels, 16000 samples
    'channel': 0,
    'sample_frequency': 16000.0,
    'frame_shift': 10.0,  # milliseconds
    'frame_length': 25.0,  # milliseconds
    'round_to_power_of_two': True,
    'preemphasis_coefficient': 0.97,
    'window_type': 'hanning',
    'blackman_coeff': 0.42,
    'snip_edges': True,
    'raw_energy': True,
    'energy_floor': 0.0,
    'dither': 0.0,
}
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 (98, 257) — shape (98, 257) 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
get_labels Not yet run
unverified (harvested, no recorded run)
pytorch/audio/.github/process_commit.py
code served (permissive licence) · get_code("57cb0e041c9b422c")
How it ran

no invocation recorded.

get_pr_merger_and_number Not yet run
unverified (harvested, no recorded run)
pytorch/audio/.github/process_commit.py
code served (permissive licence) · get_code("9eaef367a8dc3018")
How it ran

no invocation recorded.

load_with_torchcodec Not yet run
unverified (harvested, no recorded run)
pytorch/audio/src/torchaudio/_torchcodec.py
code served (permissive licence) · get_code("48b991de09c22d05")
How it ran

no invocation recorded.

query_torchaudio Not yet run
unverified (harvested, no recorded run)
pytorch/audio/.github/process_commit.py
code served (permissive licence) · get_code("087f9d0ce1b3f939")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 6 later) and 4 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
eval_env 1 other paper
1 later
2406.02560 (2024-06)
Less Peaky and More Accurate CTC Forced Alignment by Label Priors
fail_with_message 1 other paper
1 later
2406.02560 (2024-06)
Less Peaky and More Accurate CTC Forced Alignment by Label Priors
get_labels 1 other paper
1 later
2406.02560 (2024-06)
Less Peaky and More Accurate CTC Forced Alignment by Label Priors
get_pr_merger_and_number 1 other paper
1 later
2406.02560 (2024-06)
Less Peaky and More Accurate CTC Forced Alignment by Label Priors
inverse_mel_scale 1 other paper
1 later
2601.08342 (2026-01)
Detecting Mental Manipulation in Speech via Synthetic Multi-Speaker Dialogue
query_torchaudio 1 other paper
1 later
2406.02560 (2024-06)
Less Peaky and More Accurate CTC Forced Alignment by Label Priors

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

TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing well-designed, easy-to-use, and performant PyTorch components. Its contributors routinely engage with users to understand their needs and fulfill them by developing impactful features. Here, we survey TorchAudio's development principles and contents and highlight key features we include in its latest version (2.1): self-supervised learning pre-trained pipelines and training recipes, high-performance CTC decoders, speech recognition models and training recipes, advanced media I/O capabilities, and tools for performing forced alignment, multi-channel speech enhancement, and reference-less speech assessment. For a selection of these features, through empirical studies, we demonstrate their efficacy and show that they achieve competitive or state-of-the-art performance.

For agents

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

get_harvested_code_for_paper("2310.17864")
get_code_for_paper("2310.17864")
have("2310.17864")

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

curl https://syntology.ai/api/ran/2310.17864.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.17864.svg)](https://syntology.ai/paper/2310.17864)

Connect an agent — have() is free.