SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.11477 · NeurIPS · 2020

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Abdelrahman Mohamed, Alexei Baevski, Michael Auli, Henry Zhou

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 5 have no contract verdict; 2 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/2006.11477.json · badge: /api/ran/2006.11477.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
phanxuanphucnd/wav2asr community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
vasudevgupta7/gsoc-wav2vec2 community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
mailong25/self-supervised-speech-recognition reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
add_asr_eval_argument Ran
ran; our contract draft was wrong, not the code
mailong25/self-supervised-speech-recognition/stt.py
pointer only (licence: NONE) · get_code("0f3c0e3f4461c02d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mailong25/self-supervised-speech-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_dataset_itr Ran
ran; our contract draft was wrong, not the code
mailong25/self-supervised-speech-recognition/stt.py
pointer only (licence: NONE) · get_code("732cb84e2f814ba6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mailong25/self-supervised-speech-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_from_registry Ran
ran on a synthesized input
phanxuanphucnd/wav2asr/arizona/utils/misc_utils.py
code served (permissive licence) · get_code("90190d4490581c2d")
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 Linear. 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)

# Build a registry dict with some sample entries
registry = {
    'model_a': nn.Linear(4, 3),
    'model_b': nn.Conv1d(4, 8, 3),
    'loss_fn': nn.MSELoss(),
    'optimizer': torch.optim.SGD,
}

# Test with a lowercase key that exists in registry
key = 'MODEL_A'  # Will be lowercased to 'model_a'

ARGS = {
    'key': key,
    'registry': registry,
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
ifnone Ran
ran on a synthesized input
phanxuanphucnd/wav2asr/arizona/utils/misc_utils.py
code served (permissive licence) · get_code("ea6f42601b6cb44e")
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)

# ifnone takes two parameters: a and b
# The function returns b if a is None, otherwise returns a
# So we need to test both cases

# Test case 1: a is not None
a_value = "test_string"
b_value = "default_string"

ARGS = {
    "a": a_value,
    "b": b_value,
}
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
replace Ran
ran on a synthesized input
vasudevgupta7/gsoc-wav2vec2/src/convert_torch_to_tf.py
code served (permissive licence) · get_code("e488217cd68c52ed")
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 = {
    'k': 'layer_norm.weight',
    'prefix': 'model/encoder/'
}
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
str2bool Ran
ran on a synthesized input
phanxuanphucnd/wav2asr/arizona/utils/misc_utils.py
code served (permissive licence) · get_code("9e0b1e5fd4f77016")
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 torch

torch.manual_seed(0)

ARGS = {
    'value': 'true'
}
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 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
tf_multinomial_no_replacement Ran
ran on a synthesized input
vasudevgupta7/gsoc-wav2vec2/src/wav2vec2/spec_augment.py
code served (permissive licence) · get_code("d1e7bdb6b6c8d6cb")
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 EagerTensor, ndim 2, dtype family int, shape (2, 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Create a small distribution tensor (batch_size=2, num_classes=4)
# Using a valid probability distribution (sums to 1 for each row)
distribution_np = np.array([
    [0.1, 0.2, 0.3, 0.4],
    [0.25, 0.25, 0.25, 0.25]
], dtype=np.float32)

distribution = tf.constant(distribution_np, dtype=tf.float32)

# Number of samples to draw without replacement
num_samples = 2

ARGS = {
    "distribution": distribution,
    "num_samples": num_samples
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family int, shape (2, 2) — shape (2, 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
apply_spec_augmentation Not yet run
unverified (harvested, no recorded run)
vasudevgupta7/gsoc-wav2vec2/src/wav2vec2/spec_augment.py
code served (permissive licence) · get_code("fa1c3918c88bf8f5")
How it ran

no invocation recorded.

read_tfrecords Not yet run
unverified (harvested, no recorded run)
vasudevgupta7/gsoc-wav2vec2/src/data_utils.py
code served (permissive licence) · get_code("d39dd4b7bcc000b8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 5 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
get_dataset_itr 3 other papers
3 later
2101.07597 (2021-01)
UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
2203.16965 (2022-03)
PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations
2404.08368 (2024-04)
Automatic Speech Recognition Advancements for Indigenous Languages of the Americas
get_from_registry 1 other paper
1 later
2104.00769 (2021-04)
Keyword Transformer: A Self-Attention Model for Keyword Spotting
ifnone 1 other paper
1 later
2104.00769 (2021-04)
Keyword Transformer: A Self-Attention Model for Keyword Spotting
str2bool 1 other paper
1 later
2104.00769 (2021-04)
Keyword Transformer: A Self-Attention Model for Keyword Spotting

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

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data. 1

For agents

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

get_harvested_code_for_paper("2006.11477")
get_code_for_paper("2006.11477")
have("2006.11477")

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

curl https://syntology.ai/api/ran/2006.11477.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.11477.svg)](https://syntology.ai/paper/2006.11477)

Connect an agent — have() is free.