SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09660 · 2021

WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2106.09660.json · badge: /api/ran/2106.09660.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
keonlee9420/WaveGrad2 community (classifier label)
classifier basis: plan_row
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_param_num Ran
ran, honoured the contract we drafted
keonlee9420/WaveGrad2/utils/model.py
pointer only (licence: MIT); the stored copy get_code serves, from Zz-ww/VITS-BigVGAN-SpanPSP-Chinese, is pointer only (licence: NONE) · get_code("f1cba67eb6d6e4ad")
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 Zz-ww/VITS-BigVGAN-SpanPSP-Chinese, 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.

read_lexicon Ran
ran; our contract draft was wrong, not the code
keonlee9420/WaveGrad2/synthesize.py
code served (permissive licence) · get_code("2b5c06c1ba593c3c")
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 dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary lexicon file
temp_dir = tempfile.mkdtemp()
lex_path = os.path.join(temp_dir, "lexicon.txt")

# Write a sample lexicon file with words and their phonetic representations
with open(lex_path, 'w') as f:
    f.write("hello H EH L OW\n")
    f.write("world W ER L D\n")
    f.write("HELLO H EH L OW\n")  # Duplicate of "hello" in different case
    f.write("python P Y TH AH N\n")
    f.write("test T EH S T\n")

ARGS = {
    "lex_path": lex_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 later) and 0 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
read_lexicon 11 other papers
6 dated earlier, 2 the same month, 3 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
get_param_num 9 other papers
2 dated earlier, 7 later
1712.05884 (2017-12)
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
2006.06873 (2020-06)
FastPitch: Parallel Text-to-speech with Pitch Prediction
2206.04658 (2022-06)
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
and 6 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

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

Abstract

This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence. The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform. This contrasts to the original WaveGrad vocoder which conditions on mel-spectrogram features, generated by a separate model. The iterative refinement process starts from Gaussian noise, and through a series of refinement steps (e.g., 50 steps), progressively recovers the audio sequence. WaveGrad 2 offers a natural way to trade-off between inference speed and sample quality, through adjusting the number of refinement steps. Experiments show that the model can generate high fidelity audio, approaching the performance of a state-of-the-art neural TTS system. We also report various ablation studies over different model configurations. Audio samples are available at https://wavegrad.github.io/v2.

For agents

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

get_harvested_code_for_paper("2106.09660")
get_code_for_paper("2106.09660")
have("2106.09660")

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

curl https://syntology.ai/api/ran/2106.09660.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.09660.svg)](https://syntology.ai/paper/2106.09660)

Connect an agent — have() is free.