SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.05957 · 2020

Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

11 of 19 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, 1 violated it and 6 have no contract verdict; 4 failures of our instrument; 8 no recorded run), measured 2026-11-21; 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/2005.05957.json · badge: /api/ran/2005.05957.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
NVIDIA/flowtron canonical (classifier label)
classifier basis: census
9 ran · 8 no recorded run
NVIDIA/radtts extension (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
beta_binomial_prior_distribution Ran
ran on a synthesized input
NVIDIA/flowtron/data.py
code served (permissive licence) · get_code("1ae852ad9e56e415")
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 (3, 5) 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 numpy as np
import torch
from scipy.stats import betabinom

torch.manual_seed(0)

ARGS = {
    "phoneme_count": 5,
    "mel_count": 3,
    "scaling_factor": 1.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, 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 (3, 5) — shape (3, 5) 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
NVIDIA/flowtron/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
expand_abbreviations Ran
ran; our contract draft was wrong, not the code
NVIDIA/flowtron/text/cleaners.py
code served (permissive licence) · get_code("21a7f5b332d5b72b")
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

# The function expand_abbreviations takes a single parameter: text
# It expects a string and performs regex substitutions on abbreviations

ARGS = {
    'text': 'Mrs. Smith met with Dr. Johnson and Mr. Brown at the company office. Lt. Col. Anderson was also present.'
}
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
expand_safe_abbreviations Ran
ran on a synthesized input
NVIDIA/flowtron/text/cleaners.py
code served (permissive licence) · get_code("c981f6e450532d4c")
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

# The function takes a single parameter: text (a string)
# It applies regex substitutions to expand abbreviations like "no." to "number"
# We need to provide a sample text string

text_sample = "This is no. 1 item. NO. 2 is here. No. three is fine."

ARGS = {
    'text': text_sample
}
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
NVIDIA/flowtron/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
is_feature_invalid Ran
ran, violated the contract we drafted
NVIDIA/radtts/inference_voice_conversion.py
code served (permissive licence) · get_code("8f4d7a02ebc32294")
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

torch.manual_seed(0)

# Create a small tensor for x parameter
# The function calls: torch.isnan(x).any().item(), x.sum(), x.max().item()
# So x needs to be a tensor
x = torch.randn(2, 4)

# Create a scalar value for max_val parameter
# The function compares x.max().item() > max_val
max_val = 10.0

ARGS = {
    "x": x,
    "max_val": max_val
}
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
lines_to_list Ran
ran; our contract draft was wrong, not the code
NVIDIA/radtts/inference.py
code served (permissive licence) · get_code("1c566d43cb1220ba")
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 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 tempfile
import os

# Create a temporary file with some filenames
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "filenames.txt")

with open(temp_file, 'w', encoding='utf-8') as f:
    f.write("file1.txt\n")
    f.write("file2.txt\n")
    f.write("file3.txt\n")

ARGS = {
    "filename": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 list, ndim 1, dtype family float — 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
load_filepaths_and_text Ran
ran on a synthesized input
NVIDIA/flowtron/data.py
code served (permissive licence) · get_code("3b8b2175be9ceb65")
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 list, ndim 2, 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 tempfile
import os

# Create a temporary file with sample data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt', encoding='utf-8')
temp_file.write("path/to/file1.wav|This is the first text\n")
temp_file.write("path/to/file2.wav|This is the second text\n")
temp_file.write("path/to/file3.wav|This is the third text\n")
temp_file.close()

# Also prepare a direct list argument as an alternative
filelist_as_list = [
    ["path/to/file1.wav", "This is the first text"],
    ["path/to/file2.wav", "This is the second text"],
    ["path/to/file3.wav", "This is the third text"]
]

ARGS = {
    'filelist': temp_file.name,
    'split': '|'
}
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 list, ndim 2, dtype family float — 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
masked_instance_norm Ran
ran on a synthesized input
NVIDIA/flowtron/flowtron.py
code served (permissive licence) · get_code("b01e085937691049")
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 4, dtype family float, shape (2, 4, 3, 5) 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 torch.nn as nn
from typing import Optional

torch.manual_seed(0)

# Construct arguments for masked_instance_norm
batch_size = 2
num_channels = 4
spatial_dims = (3, 5)  # 2D spatial dimensions for instance norm

# Input tensor: (batch, channels, height, width)
input_tensor = torch.randn(batch_size, num_channels, *spatial_dims)

# Mask tensor: same shape as input, binary mask
mask_tensor = torch.ones(batch_size, num_channels, *spatial_dims)
# Make some values masked (0) to test masking
mask_tensor[0, 0, :2, :2] = 0.0

# Running mean and variance: shape (num_channels,)
running_mean = torch.zeros(num_channels)
running_var = torch.ones(num_channels)

# Weight and bias for affine transformation: shape (num_channels,)
weight = torch.ones(num_channels)
bias = torch.zeros(num_channels)

# Other parameters
use_input_stats = True
momentum = 0.1
eps = 1e-5

ARGS = {
    'input': input_tensor,
    'mask': mask_tensor,
    'running_mean': running_mean,
    'running_var': running_var,
    'weight': weight,
    'bias': bias,
    'use_input_stats': use_input_stats,
    'momentum': momentum,
    'eps': eps,
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
normalize_datestime Ran
ran on a synthesized input
NVIDIA/flowtron/text/datestime.py
code served (permissive licence) · get_code("9b7abc31835f4125")
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

# The function normalize_datestime takes a single parameter: text (a string)
# Looking at the function body:
# - It uses re.sub() which operates on strings
# - It expects text to be a string that may contain time patterns

ARGS = {
    'text': '2:30pm meeting at 14:45 tomorrow or 9AM sharp'
}
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
reduce_tensor Ran
ran on a synthesized input
NVIDIA/flowtron/distributed.py
code served (permissive licence) · get_code("a9bfcbb1d3623ba1")
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
import torch.distributed as dist
from unittest.mock import MagicMock, patch

torch.manual_seed(0)

# Mock dist.all_reduce and dist.ReduceOp since we're in a CPU-only environment
# without actual distributed setup
original_all_reduce = dist.all_reduce
original_reduce_op = dist.ReduceOp

def mock_all_reduce(tensor, op=None):
    """Mock all_reduce that just returns without doing distributed ops"""
    pass

# Patch the distributed module for this execution
dist.all_reduce = mock_all_reduce

# Create a small tensor to pass
tensor = torch.randn(2, 4)

# Number of GPUs
num_gpus = 2

ARGS = {
    "tensor": tensor,
    "num_gpus": num_gpus,
}
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
apply_gradient_allreduce Not yet run
unverified (harvested, no recorded run)
NVIDIA/flowtron/distributed.py
code served (permissive licence) · get_code("360725578b4657a7")
How it ran

no invocation recorded.

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

no invocation recorded.

get_gate_mask_from_lengths Not yet run
unverified (harvested, no recorded run)
NVIDIA/flowtron/flowtron.py
code served (permissive licence) · get_code("3141eb646dea4007")
How it ran

no invocation recorded.

get_mask_from_lengths Not yet run
unverified (harvested, no recorded run)
NVIDIA/flowtron/flowtron.py
code served (permissive licence) · get_code("18801918bcbf3ee3")
How it ran

no invocation recorded.

load_wav_to_torch Not yet run
unverified (harvested, no recorded run)
NVIDIA/flowtron/data.py
code served (permissive licence) · get_code("df8c980fa0466884")
How it ran

no invocation recorded.

plot_alignment_to_numpy Not yet run
unverified (harvested, no recorded run)
NVIDIA/flowtron/flowtron_plotting_utils.py
code served (permissive licence) · get_code("3d89a23ee4d0b639")
How it ran

no invocation recorded.

plot_gate_outputs_to_numpy Not yet run
unverified (harvested, no recorded run)
NVIDIA/flowtron/flowtron_plotting_utils.py
code served (permissive licence) · get_code("31de3dd8eeb3830a")
How it ran

no invocation recorded.

save_figure_to_numpy Not yet run
unverified (harvested, no recorded run)
NVIDIA/flowtron/flowtron_plotting_utils.py
code served (permissive licence) · get_code("29d749e3e95fa41d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 8 later) and 10 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
griffin_lim 14 other papers
7 dated earlier, 2 the same month, 5 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
8 dated earlier, 2 the same month, 3 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
expand_abbreviations 8 other papers
1 dated earlier, 1 the same month, 6 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?
2105.06337 (2021-05)
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
and 5 more not named here
expand_numbers 4 other papers
1 dated earlier, 3 later
1703.10135 (2017-03)
Tacotron: Towards End-to-End Speech Synthesis
2105.06337 (2021-05)
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
and 1 more not named here
save_figure_to_numpy 4 other papers
1 dated earlier, 3 later
1907.04448 (2019-07)
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
2212.14518 (2022-12)
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
and 1 more not named here
apply_gradient_allreduce 2 other papers
1 dated earlier, 1 later
1811.00002 (2018-11)
WaveGlow: A Flow-based Generative Network for Speech Synthesis
2009.01776 (2020-09)
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis
load_wav_to_torch 2 other papers
2 dated earlier
1811.00002 (2018-11)
WaveGlow: A Flow-based Generative Network for Speech Synthesis
1912.01219 (2019-12)
WaveFlow: A Compact Flow-based Model for Raw Audio
plot_alignment_to_numpy 2 other papers
1 dated earlier, 1 later
1907.04448 (2019-07)
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
reduce_tensor 1 other paper
1 later
2009.01776 (2020-09)
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opinion scores (MOS) show that Flowtron matches state-of-the-art TTS models in terms of speech quality. In addition, we provide results on control of speech variation, interpolation between samples and style transfer between speakers seen and unseen during training. Code and pre-trained models will be made publicly available at https://github.com/NVIDIA/flowtron

For agents

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

get_harvested_code_for_paper("2005.05957")
get_code_for_paper("2005.05957")
have("2005.05957")

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

curl https://syntology.ai/api/ran/2005.05957.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.05957.svg)](https://syntology.ai/paper/2005.05957)

Connect an agent — have() is free.