SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.10394 · 2021

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 0 have no contract verdict; 3 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/2107.10394.json · badge: /api/ran/2107.10394.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
yl4579/StarGANv2-VC canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
build_optimizer Ran
ran; our contract draft was wrong, not the code
yl4579/StarGANv2-VC/optimizers.py
code served (permissive licence) · get_code("f5f1bd6b9f51a9f0")
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 MultiOptimizer. 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 torch.optim import AdamW

torch.manual_seed(0)

# Create small neural network modules for parameter groups
class SmallModel1(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

class SmallModel2(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate models
model1 = SmallModel1()
model2 = SmallModel2()

# Create parameter dictionaries for each optimizer
parameters_dict = {
    'optimizer1': model1.parameters(),
    'optimizer2': model2.parameters(),
}

# Create scheduler parameters dictionary
scheduler_params_dict = {
    'optimizer1': {
        'max_lr': 0.0002,
        'epochs': 10,
        'steps_per_epoch': 100,
        'pct_start': 0.1,
    },
    'optimizer2': {
        'max_lr': 0.0001,
        'epochs': 10,
        'steps_per_epoch': 100,
        'pct_start': 0.05,
    },
}

ARGS = {
    'parameters_dict': parameters_dict,
    'scheduler_params_dict': scheduler_params_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 MultiOptimizer — a MultiOptimizer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiOptimizer 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
define_scheduler Ran
ran; our contract draft was wrong, not the code
yl4579/StarGANv2-VC/optimizers.py
code served (permissive licence) · get_code("6e710fd26220eb49")
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 OneCycleLR. 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 simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create params dictionary with all the parameters that OneCycleLR expects
params = {
    'max_lr': 0.1,
    'epochs': 200,
    'steps_per_epoch': 1000,
    'pct_start': 0.3
}

ARGS = {
    'optimizer': optimizer,
    'params': params
}
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 OneCycleLR — a OneCycleLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OneCycleLR 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
log_norm Ran
ran; our contract draft was wrong, not the code
yl4579/StarGANv2-VC/losses.py
code served (permissive licence) · get_code("62618bc8a2fb233e")
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 for x
# The function expects x to be a tensor that will be normalized along dim=2
# Shape: (batch=2, features=4, dim_to_reduce=3)
x = torch.randn(2, 4, 3)

ARGS = {
    "x": x,
    "mean": -4,
    "std": 4,
    "dim": 2
}
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
build_model Not yet run
unverified (harvested, no recorded run)
yl4579/StarGANv2-VC/models.py
code served (permissive licence) · get_code("c2745ce10c8becab")
How it ran

no invocation recorded.

compute_g_loss Not yet run
unverified (harvested, no recorded run)
yl4579/StarGANv2-VC/losses.py
code served (permissive licence) · get_code("eee2cb8319f160f7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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
build_optimizer 4 other papers
4 later
2205.15439 (2022-05)
StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis
2212.14227 (2022-12)
StyleTTS-VC: One-Shot Voice Conversion by Knowledge Transfer from Style-Based TTS Models
2309.07586 (2023-09)
Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion
and 1 more not named here
define_scheduler 4 other papers
4 later
2205.15439 (2022-05)
StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis
2212.14227 (2022-12)
StyleTTS-VC: One-Shot Voice Conversion by Knowledge Transfer from Style-Based TTS Models
2309.07586 (2023-09)
Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion
and 1 more not named here
log_norm 2 other papers
2 later
2309.07586 (2023-09)
Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion
2309.07592 (2023-09)
StarGAN-VC++: Towards Emotion Preserving Voice Conversion Using Deep Embeddings

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 present an unsupervised non-parallel many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Using a combination of adversarial source classifier loss and perceptual loss, our model significantly outperforms previous VC models. Although our model is trained only with 20 English speakers, it generalizes to a variety of voice conversion tasks, such as any-to-many, cross-lingual, and singing conversion. Using a style encoder, our framework can also convert plain reading speech into stylistic speech, such as emotional and falsetto speech. Subjective and objective evaluation experiments on a non-parallel many-to-many voice conversion task revealed that our model produces natural sounding voices, close to the sound quality of state-of-the-art text-to-speech (TTS) based voice conversion methods without the need for text labels. Moreover, our model is completely convolutional and with a faster-than-real-time vocoder such as Parallel WaveGAN can perform real-time voice conversion.

For agents

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

get_harvested_code_for_paper("2107.10394")
get_code_for_paper("2107.10394")
have("2107.10394")

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

curl https://syntology.ai/api/ran/2107.10394.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.10394.svg)](https://syntology.ai/paper/2107.10394)

Connect an agent — have() is free.