SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.17016 · 2022

Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 3 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/2210.17016.json · badge: /api/ran/2210.17016.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
BUTSpeechFIT/wespeaker_ssl_public community (classifier label)
classifier basis not recorded on the link
7 ran · 3 no recorded run
FunctionStatusWhere it lives
contrastive_collate_fn Ran
ran on a synthesized input
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/ssl/dataset/dataset.py
code served (permissive licence) · get_code("e7dc5569bb9b9f5d")
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 torch

torch.manual_seed(0)

# The function expects a batch which is a list of sample dicts
# Each sample_dict has a 'feat' key with 'local_chunks' and 'global_chunks'
# These are lists/iterables that can be stacked with torch.stack

batch = [
    {
        'feat': {
            'local_chunks': [torch.randn(4, 3), torch.randn(4, 3)],
            'global_chunks': [torch.randn(5, 3), torch.randn(5, 3)]
        }
    },
    {
        'feat': {
            'local_chunks': [torch.randn(4, 3), torch.randn(4, 3)],
            'global_chunks': [torch.randn(5, 3), torch.randn(5, 3)]
        }
    }
]

ARGS = {
    'batch': batch
}
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 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
dino_collate_fn Ran
ran on a synthesized input
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/ssl/dataset/dataset.py
code served (permissive licence) · get_code("0b7b70c22d6a66dd")
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 torch

torch.manual_seed(0)

# Construct a batch of sample dictionaries that matches what dino_collate_fn expects
batch = [
    {
        'key': 'sample_0',
        'label': 0,
        'feat': {
            'local_chunks': [torch.randn(4, 3), torch.randn(4, 3)],
            'global_chunks': [torch.randn(5, 3), torch.randn(5, 3)]
        }
    },
    {
        'key': 'sample_1',
        'label': 1,
        'feat': {
            'local_chunks': [torch.randn(4, 3), torch.randn(4, 3)],
            'global_chunks': [torch.randn(5, 3), torch.randn(5, 3)]
        }
    }
]

ARGS = {
    'batch': batch
}
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 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
gelu Ran
ran; our contract draft was wrong, not the code
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/models/ssl/modules.py
code served (permissive licence) · get_code("f30ebf4e48b7e2d7")
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)

# Create a small tensor with shape (2, 4)
x = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "x": x
}
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
gelu_accurate Ran
ran; our contract draft was wrong, not the code
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/models/ssl/modules.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from BytedanceSpeech/seed-tts-eval, is pointer only (licence: NONE) · get_code("4aa7333ffd7e18c6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from BytedanceSpeech/seed-tts-eval, and GitHub detected no licence in that repository 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_model_encoder_state_dict Ran
ran on a synthesized input
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/ssl/bin/average_contrastive_model.py
code served (permissive licence) · get_code("bb3c357a90bdd28c")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a state dict that mimics what a model might have
# The function looks for keys starting with 'encoder_q.' or 'encoder.'
state_dict = {
    'encoder_q.layer1.weight': torch.randn(4, 3),
    'encoder_q.layer1.bias': torch.randn(4),
    'encoder_q.layer2.weight': torch.randn(5, 4),
    'encoder.layer1.weight': torch.randn(4, 3),
    'encoder.layer1.bias': torch.randn(4),
    'other_module.weight': torch.randn(2, 2),
    'decoder.layer1.weight': torch.randn(3, 4),
}

ARGS = {
    'state_dict': state_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 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
get_t_model_state_dict Ran
ran on a synthesized input
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/ssl/bin/average_dino_model.py
code served (permissive licence) · get_code("55d78222d8e61479")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function iterates over state_dict.items() and filters keys that start with 't_model.'
# It then strips the 't_model.' prefix and builds a new dict
# So we need a state_dict (dict-like object mapping strings to tensors)

state_dict = {
    't_model.layer1.weight': torch.randn(4, 3),
    't_model.layer1.bias': torch.randn(4),
    't_model.layer2.weight': torch.randn(5, 4),
    'other_model.weight': torch.randn(3, 2),
    't_model.layer3.bias': torch.randn(2),
}

ARGS = {
    'state_dict': state_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 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
trunc_normal_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/ssl/models/dino_wrapper.py
code served (permissive licence) · get_code("fabe0899316ffaa5")
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) 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
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
compute_mask_indices Not yet run
unverified (harvested, no recorded run)
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/models/ssl/WavLM.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from BytedanceSpeech/seed-tts-eval, is pointer only (licence: NONE) · get_code("d22a5e7495dd7a3a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from BytedanceSpeech/seed-tts-eval, and GitHub detected no licence in that repository 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. No invocation recorded.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/ssl/models/moco_wrapper.py
code served (permissive licence) · get_code("73cecca9f3575f09")
How it ran

no invocation recorded.

get_activation_fn Not yet run
unverified (harvested, no recorded run)
BUTSpeechFIT/wespeaker_ssl_public/wespeaker/models/ssl/modules.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from BytedanceSpeech/seed-tts-eval, is pointer only (licence: NONE) · get_code("01233f4856456c5f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from BytedanceSpeech/seed-tts-eval, and GitHub detected no licence in that repository 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. 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 (6 with at least one paper dated earlier, 2 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
trunc_normal_ 160 other papers
42 dated earlier, 2 the same month, 115 later, 1 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
concat_all_gather 138 other papers
59 dated earlier, 2 the same month, 75 later, 2 same year, order not determinable · 33 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 135 more not named here
gelu 11 other papers
2 dated earlier, 9 later
2204.02152 (2022-04)
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
2212.09058 (2022-12)
BEATs: Audio Pre-Training with Acoustic Tokenizers
and 8 more not named here
gelu_accurate 11 other papers
2 dated earlier, 9 later
2204.02152 (2022-04)
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
2212.09058 (2022-12)
BEATs: Audio Pre-Training with Acoustic Tokenizers
and 8 more not named here
get_activation_fn 11 other papers
2 dated earlier, 9 later
2204.02152 (2022-04)
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
2212.09058 (2022-12)
BEATs: Audio Pre-Training with Acoustic Tokenizers
and 8 more not named here
compute_mask_indices 5 other papers
2 dated earlier, 3 later
2204.02152 (2022-04)
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
2305.11072 (2023-05)
Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering
and 2 more not named here

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

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://github.com/wenet-e2e/wespeaker.

For agents

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

get_harvested_code_for_paper("2210.17016")
get_code_for_paper("2210.17016")
have("2210.17016")

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

curl https://syntology.ai/api/ran/2210.17016.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.17016.svg)](https://syntology.ai/paper/2210.17016)

Connect an agent — have() is free.