SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.03218 · 2022

Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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 1 has no contract verdict; 0 failures of our instrument; 3 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/2202.03218.json · badge: /api/ran/2202.03218.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
sinhat98/adapter-wavlm community (classifier label)
classifier basis not recorded on the link
1 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_eer Ran
ran on a synthesized input
sinhat98/adapter-wavlm/ASV/utils.py
code served (permissive licence) · get_code("7d9e8cae2fb74061")
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 type. 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 numpy as np

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

# Create sample scores (cosine similarities between -1 and 1)
# Mix of same-speaker and different-speaker scores
scores = np.array([
    0.95, 0.92, 0.88, 0.85,  # Same speaker scores (high similarity)
    0.72, 0.68, 0.65, 0.60,  # Same speaker scores
    0.45, 0.40, 0.35, 0.30,  # Different speaker scores (low similarity)
    0.25, 0.20, 0.15, 0.10,  # Different speaker scores
], dtype=np.float32)

# Create corresponding labels: 1 for same speaker, 0 for different
labels = np.array([
    1, 1, 1, 1,  # Same speaker
    1, 1, 1, 1,  # Same speaker
    0, 0, 0, 0,  # Different speaker
    0, 0, 0, 0,  # Different speaker
], dtype=np.int32)

ARGS = {
    'scores': scores,
    'labels': labels,
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
train_model Not yet run
unverified (harvested, no recorded run)
sinhat98/adapter-wavlm/ASR/utils.py
code served (permissive licence) · get_code("50073445dcd27d41")
How it ran

no invocation recorded.

train_model Not yet run
unverified (harvested, no recorded run)
sinhat98/adapter-wavlm/IC/utils.py
code served (permissive licence) · get_code("0d1a99e9f22651f8")
How it ran

no invocation recorded.

train_model Not yet run
unverified (harvested, no recorded run)
sinhat98/adapter-wavlm/SER/utils.py
code served (permissive licence) · get_code("ba15c6222ac9f5a2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these models are fine-tuned on a small amount of labeled data for a downstream task such as Automatic Speech Recognition (ASR). This involves re-training the majority of the model for each task. Adapters are small lightweight modules which are commonly used in Natural Language Processing (NLP) to adapt pre-trained models to new tasks. In this paper we propose applying adapters to wav2vec 2.0 to reduce the number of parameters required for downstream ASR tasks, and increase scalability of the model to multiple tasks or languages. Using adapters we can perform ASR while training fewer than 10% of parameters per task compared to full fine-tuning with little degradation of performance. Ablations show that applying adapters into just the top few layers of the pre-trained network gives similar performance to full transfer, supporting the theory that higher pre-trained layers encode more phonemic information, and further optimizing efficiency.

For agents

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

get_harvested_code_for_paper("2202.03218")
get_code_for_paper("2202.03218")
have("2202.03218")

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

curl https://syntology.ai/api/ran/2202.03218.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.03218.svg)](https://syntology.ai/paper/2202.03218)

Connect an agent — have() is free.