SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.06337 · 2021

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech

arXiv · PDF · Open in the Atlas

Code that ran

15 of 18 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, 2 violated it and 3 have no contract verdict; 9 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/2105.06337.json · badge: /api/ran/2105.06337.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
WelkinYang/GradTTS community (classifier label)
classifier basis not recorded on the link
12 ran · 3 no recorded run
playvoice/grad-svc extension (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
default Ran
ran, violated the contract we drafted
WelkinYang/GradTTS/unet.py
code served (permissive licence) · get_code("fbf9ec7be545688e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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
import numpy as np
from inspect import isfunction

torch.manual_seed(0)

# Test case 1: val exists (not None), d is a regular value
val_case1 = 42
d_case1 = 100

# Test case 2: val is None, d is a regular value
val_case2 = None
d_case2 = "default_string"

# Test case 3: val is None, d is a function
val_case3 = None
def d_case3():
    return [1, 2, 3]

# Test case 4: val exists, d is a function (function should not be called)
val_case4 = torch.tensor([1.0, 2.0, 3.0])
def d_case4():
    return torch.tensor([4.0, 5.0, 6.0])

# We'll use case 2 for the main ARGS
ARGS = {
    'val': None,
    'd': "default_value"
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, 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
duration_loss Ran
ran on a synthesized input
WelkinYang/GradTTS/commons.py
code served (permissive licence) · get_code("2b6c52ad9b61c287")
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 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)

# logw: predicted log duration (tensor)
# logw_: target log duration (tensor)
# lengths: sequence lengths for normalization (tensor)

# Create small tensors with distinct sizes for clarity
batch_size = 2
max_length = 4

# logw: predicted log durations, shape (batch_size, max_length)
logw = torch.randn(batch_size, max_length)

# logw_: target log durations, same shape as logw
logw_ = torch.randn(batch_size, max_length)

# lengths: actual lengths of sequences for each item in batch, shape (batch_size,)
lengths = torch.tensor([3, 4], dtype=torch.float32)

ARGS = {
    "logw": logw,
    "logw_": logw_,
    "lengths": lengths,
}
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 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
dynamic_range_compression Ran
ran; our contract draft was wrong, not the code
WelkinYang/GradTTS/audio_processing.py
code served (permissive licence) · get_code("83e2c862f7374ac7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 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

torch.manual_seed(0)

# Create a small tensor with positive values for dynamic range compression
# This simulates magnitude spectrogram or similar audio processing data
x = torch.rand(2, 4) * 10  # Random values between 0 and 10

# C is compression factor (default 1)
C = 1

# clip_val is minimum clipping value (default 1e-05)
clip_val = 1e-05

ARGS = {
    'x': x,
    'C': C,
    'clip_val': clip_val
}
Setup block drafted by
a language model, Claude Sonnet 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
exists Ran
ran, violated the contract we drafted
WelkinYang/GradTTS/unet.py
code served (permissive licence) · get_code("608e364a9d2376a3")
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 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

def exists(x):
    return x is not None

ARGS = {
    "x": torch.tensor([1, 2, 3, 4])
}
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 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
expand_abbreviations Ran
ran; our contract draft was wrong, not the code
WelkinYang/GradTTS/text/cleaners.py
code served (permissive licence) · get_code("cea1f83e9db28ed8")
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 re

def expand_abbreviations(text):
    _abbreviations = [(re.compile('\\b%s\\.' % x[0], re.IGNORECASE), x[1]) for x in [('mrs', 'misess'), ('mr', 'mister'), ('dr', 'doctor'), ('st', 'saint'), ('co', 'company'), ('jr', 'junior'), ('maj', 'major'), ('gen', 'general'), ('drs', 'doctors'), ('rev', 'reverend'), ('lt', 'lieutenant'), ('hon', 'honorable'), ('sgt', 'sergeant'), ('capt', 'captain'), ('esq', 'esquire'), ('ltd', 'limited'), ('col', 'colonel'), ('ft', 'fort')]]
    for regex, replacement in _abbreviations:
        text = re.sub(regex, replacement, text)
    return text

ARGS = {
    'text': 'Dr. Smith and Mrs. Johnson went to the fort. Mr. Brown is a colonel.'
}
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 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
griffin_lim Ran
ran; our contract draft was wrong, not the code
WelkinYang/GradTTS/audio_processing.py
code served (permissive licence) · get_code("9f9ec26d4cdfdf7d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 11) 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 numpy as np

torch.manual_seed(0)

class STFT:
    def __init__(self):
        pass
    
    def transform(self, signal):
        # Returns (magnitudes, angles)
        # signal shape: (batch, time)
        batch_size = signal.size(0)
        time_len = signal.size(1)
        # Return magnitudes and angles with shape (batch, freq, time_frames)
        freq_bins = 5
        time_frames = 7
        magnitudes = torch.abs(torch.randn(batch_size, freq_bins, time_frames))
        angles = torch.randn(batch_size, freq_bins, time_frames)
        return magnitudes, angles
    
    def inverse(self, magnitudes, angles):
        # magnitudes shape: (batch, freq, time_frames)
        # angles shape: (batch, freq, time_frames)
        # Returns signal with shape (batch, 1, time)
        batch_size = magnitudes.size(0)
        time_len = 11
        signal = torch.randn(batch_size, 1, time_len)
        return signal

stft_fn = STFT()

# Create magnitudes tensor with shape (batch=2, freq=5, time_frames=7)
magnitudes = torch.abs(torch.randn(2, 5, 7))

ARGS = {
    'magnitudes': magnitudes,
    'stft_fn': stft_fn,
    'n_iters': 3
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, 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, 11) — shape (2, 11) 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
intersperse Ran
ran; our contract draft was wrong, not the code
WelkinYang/GradTTS/commons.py
pointer only (licence: MIT); the stored copy get_code serves, from wxzyd123/pivotal_objective_perturbation, is pointer only (licence: NONE) · get_code("c01a3efb274ff778")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from wxzyd123/pivotal_objective_perturbation, 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.

latest_checkpoint_path Ran
ran; our contract draft was wrong, not the code
WelkinYang/GradTTS/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from hayeong0/Diff-HierVC, is pointer only (licence: NONE) · get_code("321604dda57bb02d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from hayeong0/Diff-HierVC, 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.

load_bigv_model Ran
ran; our contract draft was wrong, not the code
playvoice/grad-svc/gvc_inference.py
code served (permissive licence) · get_code("98cc9f3aed7a8480")
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 MinimalModel. 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
import tempfile
import os

torch.manual_seed(0)

# Create a minimal model class that has state_dict() and load_state_dict() methods
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.conv = nn.Conv1d(2, 5, 3)
    
    def forward(self, x):
        return x

# Instantiate the model
model = MinimalModel()

# Create a temporary checkpoint file with the expected structure
checkpoint_dict = {
    'model_g': {
        'linear.weight': torch.randn(3, 4),
        'linear.bias': torch.randn(3),
        'conv.weight': torch.randn(5, 2, 3),
        'conv.bias': torch.randn(5),
    }
}

# Write checkpoint to a temporary file
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pt') as f:
    checkpoint_path = f.name
    torch.save(checkpoint_dict, f)

ARGS = {
    'checkpoint_path': checkpoint_path,
    'model': model,
}
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 MinimalModel — a MinimalModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MinimalModel 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
load_checkpoint Ran
ran on a synthesized input
WelkinYang/GradTTS/utils.py
code served (permissive licence) · get_code("a4324b03a174abb9")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import tempfile
import os

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal optimizer
model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a checkpoint dictionary
checkpoint_dict = {
    'model': model.state_dict(),
    'optimizer': optimizer.state_dict(),
    'iteration': 42,
    'learning_rate': 0.001
}

# Write checkpoint to a temporary file
with tempfile.NamedTemporaryFile(delete=False, suffix='.pt') as f:
    checkpoint_path = f.name
    torch.save(checkpoint_dict, checkpoint_path)

# Create fresh model and optimizer for loading
loaded_model = SimpleModel()
loaded_optimizer = torch.optim.SGD(loaded_model.parameters(), lr=0.01)

ARGS = {
    'checkpoint_path': checkpoint_path,
    'model': loaded_model,
    'optimizer': loaded_optimizer
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
load_gvc_model Ran
ran; our contract draft was wrong, not the code
playvoice/grad-svc/gvc_inference.py
code served (permissive licence) · get_code("051895a532dbea48")
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 SimpleModel. 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
import tempfile
import os

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleModel()

# Create a checkpoint file with model state
checkpoint_dict = {
    'model': model.state_dict()
}

# Create temporary checkpoint file
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pt') as f:
    checkpoint_path = f.name
    torch.save(checkpoint_dict, checkpoint_path)

try:
    ARGS = {
        'checkpoint_path': checkpoint_path,
        'model': model
    }
finally:
    # Clean up will happen after ARGS is defined
    pass
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
lowercase Ran
ran on a synthesized input
WelkinYang/GradTTS/text/cleaners.py
code served (permissive licence) · get_code("296274b940cb0b32")
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 = {
    "text": "Hello World"
}
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
mle_loss Ran
ran; our contract draft was wrong, not the code
WelkinYang/GradTTS/commons.py
code served (permissive licence) · get_code("7e3430bd9ded8745")
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 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
import math

torch.manual_seed(0)

# Create small tensors for the function parameters
# z: latent variable tensor, shape (2, 4)
z = torch.randn(2, 4)

# m: mean tensor, same shape as z
m = torch.randn(2, 4)

# logs: log-scale tensor, same shape as z
logs = torch.randn(2, 4)

# mask: binary mask tensor, same shape as z
mask = torch.ones(2, 4)

ARGS = {
    "z": z,
    "m": m,
    "logs": logs,
    "mask": mask,
}
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 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
num_to_groups Ran
ran, honoured the contract we drafted
WelkinYang/GradTTS/unet.py
code served (permissive licence) · get_code("4f66ae7f14b3b240")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

torch.manual_seed(0)

# Analyze the function:
# - num_to_groups takes two parameters: num and divisor
# - num is used in integer division (//) and modulo (%)
# - divisor is used in integer division (//) and modulo (%), and appended to a list
# - Both should be integers

ARGS = {
    "num": 17,
    "divisor": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
read_lexicon Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from KevinMIN95/StyleSpeech
pointer only · get_code("2b5c06c1ba593c3c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

expand_numbers Not yet run
unverified (harvested, no recorded run)
WelkinYang/GradTTS/text/cleaners.py
code served (permissive licence) · get_code("4c6716f6a3894fe8")
How it ran

no invocation recorded.

plot_spectrogram_to_numpy Not yet run
unverified (harvested, no recorded run)
WelkinYang/GradTTS/utils.py
code served (permissive licence) · get_code("9dc202f235585e84")
How it ran

no invocation recorded.

update_model Not yet run
unverified (harvested, no recorded run)
WelkinYang/GradTTS/waveglow/convert_model.py
code served (permissive licence) · get_code("22c86725da4140b0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 17 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 3 the same month, 17 later) and 1 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
default 207 other papers
6 dated earlier, 1 the same month, 200 later · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
exists 144 other papers
7 dated earlier, 1 the same month, 136 later · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 more not named here
griffin_lim 14 other papers
10 dated earlier, 4 later
1803.09017 (2018-03)
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
1811.02122 (2018-11)
Robust and fine-grained prosody control of end-to-end speech synthesis
1812.04342 (2018-12)
Learning latent representations for style control and transfer in end-to-end speech synthesis
and 11 more not named here
dynamic_range_compression 13 other papers
11 dated earlier, 2 later
1803.09017 (2018-03)
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
1811.02122 (2018-11)
Robust and fine-grained prosody control of end-to-end speech synthesis
1812.04342 (2018-12)
Learning latent representations for style control and transfer in end-to-end speech synthesis
and 10 more not named here
intersperse 13 other papers
1 dated earlier, 12 later
2005.11129 (2020-05)
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
2204.09079 (2022-04)
Music Source Separation with Generative Flow
and 10 more not named here
read_lexicon 11 other papers
4 dated earlier, 1 the same month, 6 later
1905.09263 (2019-05)
FastSpeech: Fast, Robust and Controllable Text to Speech
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2006.06873 (2020-06)
FastPitch: Parallel Text-to-speech with Pitch Prediction
and 8 more not named here
expand_abbreviations 8 other papers
3 dated earlier, 5 later
1703.10135 (2017-03)
Tacotron: Towards End-to-End Speech Synthesis
2005.01245 (2020-05)
Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?
2005.05957 (2020-05)
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
and 5 more not named here
num_to_groups 8 other papers
1 dated earlier, 7 later
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2110.07579 (2021-10)
Diffusion Normalizing Flow
2111.01713 (2021-11)
Realistic galaxy image simulation via score-based generative models
and 5 more not named here
lowercase 6 other papers
3 dated earlier, 3 later
1703.10135 (2017-03)
Tacotron: Towards End-to-End Speech Synthesis
2005.01245 (2020-05)
Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?
2005.11129 (2020-05)
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
and 3 more not named here
latest_checkpoint_path 5 other papers
1 dated earlier, 4 later
2005.11129 (2020-05)
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
2305.19709 (2023-05)
XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech
and 2 more not named here
expand_numbers 4 other papers
2 dated earlier, 2 later
1703.10135 (2017-03)
Tacotron: Towards End-to-End Speech Synthesis
2005.05957 (2020-05)
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
and 1 more not named here
duration_loss 2 other papers
1 dated earlier, 1 later
2005.11129 (2020-05)
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
load_checkpoint 2 other papers
1 dated earlier, 1 later
2005.11129 (2020-05)
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
plot_spectrogram_to_numpy 2 other papers
1 dated earlier, 1 later
2005.11129 (2020-05)
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
load_bigv_model 1 other paper
1 later
2109.13821 (2021-09)
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
load_gvc_model 1 other paper
1 later
2109.13821 (2021-09)
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
mle_loss 1 other paper
1 later
2309.05027 (2023-09)
VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching

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

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing for flexible inference schemes. In this paper we introduce Grad-TTS, a novel text-to-speech model with score-based decoder producing mel-spectrograms by gradually transforming noise predicted by encoder and aligned with text input by means of Monotonic Alignment Search. The framework of stochastic differential equations helps us to generalize conventional diffusion probabilistic models to the case of reconstructing data from noise with different parameters and allows to make this reconstruction flexible by explicitly controlling trade-off between sound quality and inference speed. Subjective human evaluation shows that Grad-TTS is competitive with state-of-the-art text-to-speech approaches in terms of Mean Opinion Score. We will make the code publicly available shortly.

For agents

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

get_harvested_code_for_paper("2105.06337")
get_code_for_paper("2105.06337")
have("2105.06337")

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

curl https://syntology.ai/api/ran/2105.06337.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.06337.svg)](https://syntology.ai/paper/2105.06337)

Connect an agent — have() is free.