SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.08459 · 2019

Non-Autoregressive Neural Text-to-Speech

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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 3 have no contract verdict; 3 failures of our instrument; 1 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/1905.08459.json · badge: /api/ran/1905.08459.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
vardaan123/ParaNet community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
ksw0306/WaveVAE community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
bpe_decode Ran
ran on a synthesized input
vardaan123/ParaNet/paraphrase_en_paranet.py
code served (permissive licence) · get_code("dcb4301ac44d50ec")
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 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 re

def bpe_decode(input_str_tok):
    out = re.sub('(@@ )|(@@ ?$)', '', ' '.join(input_str_tok)).split(' ')
    return out

# input_str_tok is expected to be a list of strings (tokens)
# The function joins them with spaces, then applies regex substitution to remove @@ markers,
# then splits back into a list

ARGS = {
    'input_str_tok': ['hello', '@@', 'world', '@@', 'test']
}
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 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
collate_fn Ran
ran; our contract draft was wrong, not the code
ksw0306/WaveVAE/data.py
code served (permissive licence) · get_code("4846dec26aaad0fb")
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. 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

torch.manual_seed(0)

# Create a batch of data samples
# Each sample is a tuple of (x, c) where:
# x is a 1D array of audio samples (length T)
# c is a 2D array of conditioning features (length T_c, dimension D)
# With upsample_conditional_features=True, len(x) should be hop_length * len(c)

batch = []

# Sample 1: audio of length 256*10=2560, conditioning of length 10, feature dim 4
x1 = np.random.randn(2560).astype(np.float32)
c1 = np.random.randn(10, 4).astype(np.float32)
batch.append((x1, c1))

# Sample 2: audio of length 256*8=2048, conditioning of length 8, feature dim 4
x2 = np.random.randn(2048).astype(np.float32)
c2 = np.random.randn(8, 4).astype(np.float32)
batch.append((x2, c2))

ARGS = {
    "batch": batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
collate_fn_synthesize Ran
ran on a synthesized input
ksw0306/WaveVAE/data.py
code served (permissive licence) · get_code("ec4b02e7e489d13f")
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. 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

torch.manual_seed(0)

# The function expects a batch which is a list of tuples
# Each tuple contains (x, c) where:
# - x is a 1D numpy array of audio samples (length T)
# - c is a 2D numpy array of conditional features (length T/hop_length, feature_dim D)

# Create sample batch items
# Item 1: audio of length 512, conditional features of length 2 (512/256=2)
x1 = np.random.randn(512).astype(np.float32)
c1 = np.random.randn(2, 4).astype(np.float32)  # 2 frames, 4 features

# Item 2: audio of length 768, conditional features of length 3 (768/256=3)
x2 = np.random.randn(768).astype(np.float32)
c2 = np.random.randn(3, 4).astype(np.float32)  # 3 frames, 4 features

# Create batch as list of tuples
batch = [
    (x1, c1),
    (x2, c2)
]

ARGS = {
    "batch": batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
create_parser Ran
ran on a synthesized input
vardaan123/ParaNet/apply_bpe.py
code served (permissive licence) · get_code("92b2d4c3fefb21b7")
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 ArgumentParser. 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 sys
import argparse
import tempfile
import io

# Create temporary file objects for the required arguments
codes_content = """#version: 0.2
l o
e s
t h
"""
codes_file = io.StringIO(codes_content)

# Create optional vocabulary file
vocab_content = """hello 100
world 95
the 200
"""
vocab_file = io.StringIO(vocab_content)

# Create input and output file objects
input_file = io.StringIO("hello world\nthe quick brown fox\n")
output_file = io.StringIO()

ARGS = {
    'subparsers': None,
}
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 ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
encode Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vardaan123/ParaNet/apply_bpe.py
code served (permissive licence) · get_code("52d69829a4cee830")
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 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

# Set random seed for reproducibility
torch.manual_seed(0)

# Build the arguments dictionary for the encode function
ARGS = {
    "orig": "hello",
    "bpe_codes": {
        ("h", "e"): 0,
        ("he", "l"): 1,
        ("hel", "l"): 2,
        ("hell", "o"): 3,
        ("hello</w>",): 4,
    },
    "bpe_codes_reverse": {
        ("h", "e"): 0,
        ("he", "l"): 1,
        ("hel", "l"): 2,
        ("hell", "o"): 3,
    },
    "vocab": {
        "h</w>": True,
        "he</w>": True,
        "hel</w>": True,
        "hell</w>": True,
        "hello</w>": True,
        "l</w>": True,
        "o</w>": True,
    },
    "separator": "</w>",
    "version": (0, 2),
    "cache": {},
    "glossaries": set(),
}
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 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
get_pairs Ran
ran; our contract draft was wrong, not the code
vardaan123/ParaNet/apply_bpe.py
code served (permissive licence) · get_code("290febe7a42e8479")
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 set. 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

# The function get_pairs takes a word parameter
# word should be a tuple of symbols (variable-length strings)
# The function iterates through the tuple and creates pairs of consecutive elements

# Create a simple word as a tuple of symbols
word = ("h", "e", "l", "l", "o")

ARGS = {
    "word": word
}
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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
stft Not yet run
unverified (harvested, no recorded run)
ksw0306/WaveVAE/modules.py
code served (permissive licence) · get_code("644cfc3c70b57f21")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
get_pairs 258 other papers
4 dated earlier, 253 later, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
encode 2 other papers
1 dated earlier, 1 later
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1907.12484 (2019-07)
Joey NMT: A Minimalist NMT Toolkit for Novices
collate_fn 1 other paper
1 dated earlier
1807.07281 (2018-07)
ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
collate_fn_synthesize 1 other paper
1 dated earlier
1807.07281 (2018-07)
ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech

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

In this work, we propose ParaNet, a non-autoregressive seq2seq model that converts text to spectrogram. It is fully convolutional and brings 46.7 times speed-up over the lightweight Deep Voice 3 at synthesis, while obtaining reasonably good speech quality. ParaNet also produces stable alignment between text and speech on the challenging test sentences by iteratively improving the attention in a layer-by-layer manner. Furthermore, we build the parallel text-to-speech system and test various parallel neural vocoders, which can synthesize speech from text through a single feed-forward pass. We also explore a novel VAE-based approach to train the inverse autoregressive flow (IAF) based parallel vocoder from scratch, which avoids the need for distillation from a separately trained WaveNet as previous work.

For agents

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

get_harvested_code_for_paper("1905.08459")
get_code_for_paper("1905.08459")
have("1905.08459")

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

curl https://syntology.ai/api/ran/1905.08459.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.08459.svg)](https://syntology.ai/paper/1905.08459)

Connect an agent — have() is free.