Browse › Audio › Speech Recognition › LibriSpeech test-clean
LibriSpeech test-clean Benchmark (Speech Recognition)
Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.
The archive carries no text for this table; the description above is the archive's text for the task Speech Recognition. archive 2025-07-28
Over time archive 2025-07-28
The chart needs JavaScript; the table below carries every value.
Direction inferred from the metric name, not from the archive: Word Error Rate (WER) (lower is better). Points are placed at the row's paper date; 60 of 64 rows carry one.
Results archive 2025-07-28
Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.
| Paper | Code | Ran Syntology | Report | |||||
|---|---|---|---|---|---|---|---|---|
| 1 | United Med ASR | 0.985 | ✓ | Paper | – | 2024 | no code linked | report |
| 2 | SAMBA ASR | 1.17 | ✓ | Paper | – | 2025 | no code linked | report |
| 3 | FAdam | 1.34 | ✓ | Paper | Code | 2024 | linked, not harvested | report |
| 4 | Conformer + Wav2vec 2.0 + SpecAugment-based Noisy Student Training with Libri-Light | 1.4 | ✓ | Paper | Code | 2020 | 2 of 2 ran · 0 unverified | report |
| 5 | w2v-BERT XXL | 1.4 | ✓ | Paper | Code | 2021 | linked, not harvested | report |
| 6 | parakeet-rnnt-1.1b | 1.46 | ✓ | Paper | – | 2023 | no code linked | report |
| 7 | Conv + Transformer + wav2vec2.0 + pseudo labeling | 1.5 | ✓ | Paper | Code | 2020 | linked, not harvested | report |
| 8 | ContextNet + SpecAugment-based Noisy Student Training with Libri-Light | 1.7 | ✓ | Paper | Code | 2020 | linked, not harvested | report |
| 9 | SpeechStew (1B) | 1.7 | ✓ | Paper | – | 2021 | no code linked | report |
| 10 | Multistream CNN with Self-Attentive SRU (WER includes text normalization) | 1.75 | ✓ | Paper | – | 2020 | no code linked | report |
| 11 | Stateformer | 1.76 | – | Paper | – | 2023 | no code linked | report |
| 12 | wav2vec 2.0 with Libri-Light | 1.8 | ✓ | Paper | Code | 2020 | 2 of 9 ran · 7 unverified | report |
| 13 | HuBERT with Libri-Light | 1.8 | ✓ | Paper | Code | 2021 | 0 of 9 ran · 9 unverified | report |
| 14 | WavLM Large | 1.8 | – | Paper | Code | 2021 | linked, not harvested | report |
| 15 | E-Branchformer (L) + Internal Language Model Estimation | 1.81 | – | Paper | Code | 2022 | linked, not harvested | report |
| 16 | Zipformer+pruned transducer w/ CR-CTC (no external language model) | 1.88 | – | Paper | Code | 2024 | linked, not harvested | report |
| 17 | ContextNet(L) | 1.9 | – | Paper | Code | 2020 | linked, not harvested | report |
| 18 | Conformer(L) | 1.9 | – | Paper | Code | 2020 | 4 of 7 ran · 3 unverified | report |
| 19 | Transformer+Time reduction+Self Knowledge distillation | 1.9 | – | Paper | – | 2021 | no code linked | report |
| 20 | ContextNet(M) | 2 | ✓ | Paper | Code | 2020 | linked, not harvested | report |
| 21 | Transformer Transducer | 2.0 | – | Paper | Code | 2020 | linked, not harvested | report |
| 22 | Conformer(M) | 2 | ✓ | Paper | Code | 2020 | 4 of 7 ran · 3 unverified | report |
| 23 | SpeechStew (100M) | 2.0 | – | Paper | – | 2021 | no code linked | report |
| 24 | Qwen-Audio | 2.0 | – | Paper | Code | 2023 | 5 of 7 ran · 2 unverified | report |
| 25 | Zipformer+pruned transducer (no external language model) | 2.00 | – | Paper | Code | 2023 | linked, not harvested | report |
| 26 | Zipformer+CR-CTC (no external language model) | 2.02 | – | Paper | Code | 2024 | linked, not harvested | report |
| 27 | Conv + Transformer AM + Pseudo-Labeling (ConvLM with Transformer Rescoring) | 2.03 | – | Paper | Code | 2019 | linked, not harvested | report |
| 28 | Conv + Transformer AM + Iterative Pseudo-Labeling (n-gram LM + Transformer Rescoring) | 2.10 | – | Paper | Code | 2020 | linked, not harvested | report |
| 29 | CTC + Transformer LM rescoring | 2.10 | – | Paper | – | 2020 | no code linked | report |
| 30 | Conformer(S) | 2.1 | – | Paper | Code | 2020 | 4 of 7 ran · 3 unverified | report |
| 31 | Branchformer + GFSA | 2.11 | – | Paper | Code | 2023 | 19 of 29 ran · 10 unverified | report |
| 32 | Multi-Stream Self-Attention With Dilated 1D Convolutions | 2.20 | – | Paper | Code | 2019 | 1 of 1 ran · 0 unverified | report |
| 33 | LSTM Transducer | 2.23 | ✓ | Paper | Code | 2021 | linked, not harvested | report |
| 34 | Hybrid + Transformer LM rescoring | 2.26 | – | Paper | – | 2019 | no code linked | report |
| 35 | Hybrid model with Transformer rescoring | 2.3 | – | Paper | Code | 2019 | linked, not harvested | report |
| 36 | ContextNet(S) | 2.3 | ✓ | Paper | Code | 2020 | linked, not harvested | report |
| 37 | Conv + Transformer AM (ConvLM with Transformer Rescoring) (LS only) | 2.31 | – | Paper | Code | 2019 | linked, not harvested | report |
| 38 | Squeezeformer (L) | 2.47 | – | Paper | Code | 2022 | 31 of 49 ran · 18 unverified | report |
| 39 | LAS + SpecAugment | 2.5 | ✓ | Paper | Code | 2019 | 1 of 18 ran · 17 unverified | report |
| 40 | Transformer | 2.6 | ✓ | Paper | Code | 2019 | linked, not harvested | report |
| 41 | QuartzNet15x5 | 2.69 | – | Paper | Code | 2019 | 3 of 12 ran · 9 unverified | report |
| 42 | LAS (no LM) | 2.7 | ✓ | Paper | Code | 2019 | 1 of 18 ran · 17 unverified | report |
| 43 | wav2vec_wav2letter | 2.7 | – | Paper | Code | 2020 | linked, not harvested | report |
| 44 | Espresso | 2.8 | – | Paper | Code | 2019 | 1 of 1 ran · 0 unverified | report |
| 45 | Jasper DR 10x5 (+ Time/Freq Masks) | 2.84 | – | Paper | Code | 2019 | linked, not harvested | report |
| 46 | Jasper DR 10x5 | 2.95 | – | Paper | Code | 2019 | linked, not harvested | report |
| 47 | tdnn + chain + rnnlm rescoring | 3.06 | – | Paper | – | 2018 | no code linked | report |
| 48 | Convolutional Speech Recognition | 3.26 | ✓ | Paper | – | 2018 | no code linked | report |
| 49 | MT4SSL | 3.4 | – | Paper | Code | 2022 | linked, not harvested | report |
| 50 | Model Unit Exploration | 3.60 | – | Paper | Code | 2019 | linked, not harvested | report |
| 51 | Seq-to-seq attention | 3.82 | ✓ | Paper | Code | 2018 | 0 of 12 ran · 12 unverified | report |
| 52 | CTC-CRF 4gram-LM | 4.09 | – | Paper | Code | 2019 | linked, not harvested | report |
| 53 | HMM-TDNN trained with MMI + data augmentation (speed) + iVectors + 3 regularizations | 4.3 | – | – | – | not matched | report | |
| 54 | Centaurus (30 M) | 4.4 | – | Paper | – | 2025 | no code linked | report |
| 55 | HMM-TDNN + iVectors | 4.8 | ✓ | – | – | not matched | report | |
| 56 | Gated ConvNets | 4.8 | – | Paper | Code | 2017 | linked, not harvested | report |
| 57 | Deep Speech 2 | 5.33 | – | Paper | Code | 2015 | 2 of 39 ran · 37 unverified | report |
| 58 | CTC + policy learning | 5.42 | – | Paper | – | 2017 | no code linked | report |
| 59 | HMM-DNN + pNorm* | 5.5 | ✓ | – | – | not matched | report | |
| 60 | Li-GRU | 6.2 | – | Paper | Code | 2018 | 5 of 6 ran · 1 unverified | report |
| 61 | Snips | 6.4 | – | Paper | Code | 2018 | 1 of 15 ran · 14 unverified | report |
| 62 | Local Prior Matching (Large Model) | 7.19 | – | Paper | Code | 2020 | linked, not harvested | report |
| 63 | HMM-(SAT)GMM | 8.0 | ✓ | – | – | not matched | report | |
| 64 | AmNet | 8.6 | – | Paper | – | 2021 | no code linked | report |
All 64 rows shown. 60 link to a paper page on this site; 24 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28
Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 18 rows have a graph line, from 15 distinct papers; 16 rows (13 papers) have at least one sample that ran. Counting each paper once: Syntology ran 77 of 216 samples; 139 unverified. Separately, 23 of those 216 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections