SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.02560 · 2023

From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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; 4 failures of our instrument; 4 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/2308.02560.json · badge: /api/ran/2308.02560.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
metavoiceio/metavoice-src community (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
FunctionStatusWhere it lives
dynamically_quantize_per_channel Ran
ran; our contract draft was wrong, not the code
metavoiceio/metavoice-src/fam/llm/fast_quantize.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from amarka8/SOCKET, is pointer only (licence: NONE) · get_code("55ec8fea60e1d7e7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from amarka8/SOCKET, 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.

get_cached_file Ran
ran on a synthesized input
metavoiceio/metavoice-src/fam/llm/inference.py
code served (permissive licence) · get_code("cf90023e439d59c2")
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 os
import tempfile
import pathlib

# Create a temporary file to use as a local file path
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_audio.wav")
with open(temp_file, 'w') as f:
    f.write("dummy audio content")

# Construct valid arguments for get_cached_file
ARGS = {
    'file_or_uri': temp_file
}
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
get_group_qparams Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
metavoiceio/metavoice-src/fam/llm/fast_quantize.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from amarka8/SOCKET, is pointer only (licence: NONE) · get_code("dbabfb89a4b530ac")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from amarka8/SOCKET, 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.

make_output_file_path Ran
ran on a synthesized input
metavoiceio/metavoice-src/fam/llm/enhancers.py
code served (permissive licence) · get_code("74026bf479b959d4")
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 os

# Construct valid arguments for make_output_file_path
ARGS = {
    "audio_file": "./input/sample_audio.wav",
    "tag": "_enhanced",
    "ext": ".wav"
}
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
multinomial_sample_one_no_sync Ran
ran; our contract draft was wrong, not the code
metavoiceio/metavoice-src/fam/llm/fast_inference_utils.py
code served (permissive licence) · get_code("5b6f45360aa68edd")
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 Tensor, ndim 2, dtype family int, shape (2, 1) 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 probs_sort
# The function expects a tensor that will be divided element-wise and then argmax'd
# Shape: (batch_size, num_classes) - using distinct dimensions
probs_sort = torch.rand(2, 4)

# Normalize to make it valid probabilities
probs_sort = probs_sort / probs_sort.sum(dim=-1, keepdim=True)

ARGS = {
    "probs_sort": probs_sort,
}
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 Tensor, ndim 2, dtype family int, shape (2, 1) — shape (2, 1) 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
pack_scales_and_zeros Ran
ran; our contract draft was wrong, not the code
metavoiceio/metavoice-src/fam/llm/fast_quantize.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from amarka8/SOCKET, is pointer only (licence: NONE) · get_code("146cdcef0c195fd7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from amarka8/SOCKET, 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.

strip_prefix Ran
ran on a synthesized input
metavoiceio/metavoice-src/fam/llm/finetune.py
code served (permissive licence) · get_code("4f354d0b20a057d8")
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 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Construct a state_dict with some keys that have an unwanted prefix
state_dict = {
    "module.layer1.weight": torch.randn(4, 3),
    "module.layer1.bias": torch.randn(4),
    "module.layer2.weight": torch.randn(5, 4),
    "other.weight": torch.randn(2, 2),
}

unwanted_prefix = "module."

ARGS = {
    "state_dict": state_dict,
    "unwanted_prefix": unwanted_prefix,
}
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 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
find_multiple Not yet run
unverified (harvested, no recorded run)
metavoiceio/metavoice-src/fam/llm/fast_model.py
code served (permissive licence) · get_code("5b392490c1dd0292")
How it ran

no invocation recorded.

get_cached_embedding Not yet run
unverified (harvested, no recorded run)
metavoiceio/metavoice-src/fam/llm/inference.py
code served (permissive licence) · get_code("000187477d99d590")
How it ran

no invocation recorded.

logits_to_probs Not yet run
unverified (harvested, no recorded run)
metavoiceio/metavoice-src/fam/llm/fast_inference_utils.py
code served (permissive licence) · get_code("9ff14bb645be7875")
How it ran

no invocation recorded.

top_p_sample Not yet run
unverified (harvested, no recorded run)
metavoiceio/metavoice-src/fam/llm/fast_inference_utils.py
code served (permissive licence) · get_code("b18c8665684fec61")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 7 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
multinomial_sample_one_no_sync 8 other papers
2 dated earlier, 6 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2306.05284 (2023-06)
Simple and Controllable Music Generation
2402.04396 (2024-02)
QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
and 5 more not named here
dynamically_quantize_per_channel 4 other papers
4 later
2408.07092 (2024-08)
Post-Training Sparse Attention with Double Sparsity
2408.11049 (2024-08)
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
2511.00351 (2025-11)
Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
and 1 more not named here
get_group_qparams 3 other papers
3 later
2408.07092 (2024-08)
Post-Training Sparse Attention with Double Sparsity
2511.00351 (2025-11)
Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
2602.06283 (2026-02)
SOCKET: SOft Collision Kernel EsTimator for Sparse Attention
pack_scales_and_zeros 3 other papers
3 later
2408.07092 (2024-08)
Post-Training Sparse Attention with Double Sparsity
2511.00351 (2025-11)
Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
2602.06283 (2026-02)
SOCKET: SOft Collision Kernel EsTimator for Sparse Attention

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

Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms conditioned on highly compressed representations. Although such methods produce impressive results, they are prone to generate audible artifacts when the conditioning is flawed or imperfect. An alternative modeling approach is to use diffusion models. However, these have mainly been used as speech vocoders (i.e., conditioned on mel-spectrograms) or generating relatively low sampling rate signals. In this work, we propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality (e.g., speech, music, environmental sounds) from low-bitrate discrete representations. At equal bit rate, the proposed approach outperforms state-of-the-art generative techniques in terms of perceptual quality. Training and, evaluation code, along with audio samples, are available on the facebookresearch/audiocraft Github page.

For agents

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

get_harvested_code_for_paper("2308.02560")
get_code_for_paper("2308.02560")
have("2308.02560")

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

curl https://syntology.ai/api/ran/2308.02560.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.02560.svg)](https://syntology.ai/paper/2308.02560)

Connect an agent — have() is free.