SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.15455 · 2022

WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 7 failures of our instrument; 0 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/2203.15455.json · badge: /api/ran/2203.15455.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
leonwlw/wenet community (classifier label)
classifier basis not recorded on the link
10 ran · 0 no recorded run
FunctionStatusWhere it lives
amp2db Ran
ran, honoured the contract we drafted
leonwlw/wenet/wenet/dataset/wav_distortion.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cffan/corp, is pointer only (licence: NONE) · get_code("7a8bbc760099542d")
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 cffan/corp, 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.

batch Ran
ran on a synthesized input
leonwlw/wenet/wenet/dataset/processor.py
code served (permissive licence) · get_code("f80d5ced1e019437")
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 generator. 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)

# Create sample data with the required structure
# Each sample must have 'key', 'feat', and 'label'
data = [
    {
        'key': 'sample_0',
        'feat': torch.randn(10, 4),  # 10 frames, 4 features
        'label': 0
    },
    {
        'key': 'sample_1',
        'feat': torch.randn(15, 4),  # 15 frames, 4 features
        'label': 1
    },
    {
        'key': 'sample_2',
        'feat': torch.randn(8, 4),   # 8 frames, 4 features
        'label': 0
    },
    {
        'key': 'sample_3',
        'feat': torch.randn(12, 4),  # 12 frames, 4 features
        'label': 1
    },
]

ARGS = {
    'data': data,
    'batch_type': 'static',
    'batch_size': 2,
    'max_frames_in_batch': 12000
}
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 generator — a generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a generator 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
db2amp Ran
ran, honoured the contract we drafted
leonwlw/wenet/wenet/dataset/wav_distortion.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cffan/corp, is pointer only (licence: NONE) · get_code("2fc2bbe453a37ecd")
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 cffan/corp, 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_frames_timestamp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
leonwlw/wenet/wenet/bin/alignment.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cffan/corp, is pointer only (licence: NONE) · get_code("2d01074c23bc90de")
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 cffan/corp, 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_poly_distortion Ran
ran; our contract draft was wrong, not the code
leonwlw/wenet/wenet/dataset/wav_distortion.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cffan/corp, is pointer only (licence: NONE) · get_code("a7f9e384e3a3e16d")
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 cffan/corp, 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.

open_or_fd Ran
ran; our contract draft was wrong, not the code
leonwlw/wenet/wenet/dataset/kaldi_io.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cffan/corp, is pointer only (licence: NONE) · get_code("df07b4faa7609d90")
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 cffan/corp, 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.

popen Ran
ran; our contract draft was wrong, not the code
leonwlw/wenet/wenet/dataset/kaldi_io.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cffan/corp, is pointer only (licence: NONE) · get_code("d9a4862872e34aad")
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 cffan/corp, 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_key Ran
ran; our contract draft was wrong, not the code
leonwlw/wenet/wenet/dataset/kaldi_io.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cffan/corp, is pointer only (licence: NONE) · get_code("aa10e48fc468d9e0")
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 cffan/corp, 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.

to_numpy Ran
ran; our contract draft was wrong, not the code
leonwlw/wenet/wenet/bin/export_onnx_cpu.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mubingshen/MLC-SLM-Baseline, is pointer only (licence: NONE) · get_code("0562154e6c98265d")
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 mubingshen/MLC-SLM-Baseline, 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.

to_numpy Ran
ran; our contract draft was wrong, not the code
leonwlw/wenet/wenet/bin/export_onnx_gpu.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mubingshen/MLC-SLM-Baseline, is pointer only (licence: NONE) · get_code("03a5062a6ac43d6d")
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 mubingshen/MLC-SLM-Baseline, 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.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 9 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 9 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
open_or_fd 2 other papers
1 dated earlier, 1 later
1910.09387 (2019-10)
Clotho: An Audio Captioning Dataset
2311.03611 (2023-11)
Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication
popen 2 other papers
1 dated earlier, 1 later
1910.09387 (2019-10)
Clotho: An Audio Captioning Dataset
2311.03611 (2023-11)
Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication
read_key 2 other papers
1 dated earlier, 1 later
1910.09387 (2019-10)
Clotho: An Audio Captioning Dataset
2311.03611 (2023-11)
Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication
to_numpy 2 other papers
2 later
2211.00522 (2022-11)
TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty
2606.10439 (2026-06)
Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling
to_numpy 2 other papers
2 later
2211.00522 (2022-11)
TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty
2606.10439 (2026-06)
Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling
amp2db 1 other paper
1 later
2311.03611 (2023-11)
Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication
db2amp 1 other paper
1 later
2311.03611 (2023-11)
Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication
get_frames_timestamp 1 other paper
1 later
2311.03611 (2023-11)
Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication
make_poly_distortion 1 other paper
1 later
2311.03611 (2023-11)
Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication

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, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model. To further improve ASR performance and facilitate various production requirements, in this paper, we present WeNet 2.0 with four important updates. (1) We propose U2++, a unified two-pass framework with bidirectional attention decoders, which includes the future contextual information by a right-to-left attention decoder to improve the representative ability of the shared encoder and the performance during the rescoring stage. (2) We introduce an n-gram based language model and a WFST-based decoder into WeNet 2.0, promoting the use of rich text data in production scenarios. (3) We design a unified contextual biasing framework, which leverages user-specific context (e.g., contact lists) to provide rapid adaptation ability for production and improves ASR accuracy in both with-LM and without-LM scenarios. (4) We design a unified IO to support large-scale data for effective model training. In summary, the brand-new WeNet 2.0 achieves up to 10\% relative recognition performance improvement over the original WeNet on various corpora and makes available several important production-oriented features.

For agents

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

get_harvested_code_for_paper("2203.15455")
get_code_for_paper("2203.15455")
have("2203.15455")

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

curl https://syntology.ai/api/ran/2203.15455.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.15455.svg)](https://syntology.ai/paper/2203.15455)

Connect an agent — have() is free.