OpenCodePapers

speech-recognition-on-librispeech-test-clean

Speech Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeWord Error Rate (WER)ModelNameReleaseDate
Introducing Resonant-1 and Resonant-1-flash0.92reson8/resonant-12026-04-08
Introducing Resonant-1 and Resonant-1-flash0.94reson8/resonant-1-flash2026-04-08
Boson AI Launches Higgs STT 3 Speech-to-Text Model✓ Link0.95bosonai/higgs-audio-v3-8b-stt-v22026-04-27
Introducing Cohere-transcribe: state-of-the-art speech recognition0.96CohereLabs/cohere-transcribe-03-20262026-03-26
High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR0.985United Med ASR2024-11-24
✓ Link1.02ibm-granite/granite-speech-4.1-2b2026-04-29
Data-Efficient On-Policy Distillation for Automatic Speech Recognition✓ Link1.03AutoArk-AI/ARK-ASR-3B2026-06-22
NLE: Non-autoregressive LLM-based ASR by Transcript Editing✓ Link1.04ibm-granite/granite-speech-4.1-2b-nar2026-04-01
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link1.05nvidia/parakeet-tdt-1.1b2024-01-25
Introducing Scribe v21.05elevenlabs/scribe_v22026-01-09
Boson AI Launches Higgs STT 3 Speech-to-Text Model✓ Link1.07bosonai/higgs-audio-v3-stt2026-03-18
Introducing Universal-3 Pro: A new class of speech language model optimized for Voice AI1.1assemblyai/universal-3-pro2026-02-03
✓ Link1.1ibm-granite/granite-4.0-1b-speech2026-03-06
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities✓ Link1.11ibm-granite/granite-speech-3.3-8b2025-06-19
Introducing Zoom AI Services1.12zoom/scribe_v12026-03-10
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link1.15nvidia/parakeet-rnnt-1.1b2023-12-27
Less is More: Accurate Speech Recognition & Translation without Web-Scale Data✓ Link1.15nvidia/canary-1b2024-02-07
1.15OpenMOSS-Team/MOSS-Transcribe-preview-2B2026-06-26
Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models1.17SAMBA ASR2025-01-06
Step-Audio 2 Technical Report1.17Step-Audio 22025-08-27
Azure Speech at Build 2026: Powering Voice Agents with Real-Time and Life-like Experiences1.19microsoft/azure-speech-06-20262026-06-04
Training and Inference Efficiency of Encoder-Decoder Speech Models✓ Link1.2nvidia/canary-1b-flash2025-03-07
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities✓ Link1.21ibm-granite/granite-speech-3.3-2b2025-06-19
Voxtral✓ Link1.23mistralai/Voxtral-Small-24B-25072025-07-15
✓ Link1.23nvidia/canary-qwen-2.5b2025-07-17
Qwen3-ASR Technical Report✓ Link1.24Qwen/Qwen3-ASR-1.7B2026-01-28
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link1.25nvidia/parakeet-rnnt-0.6b2023-12-28
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link1.27nvidia/parakeet-tdt-0.6b-v22025-05-01
Avalon: ASR for Human-AI Interaction1.27aquavoice/avalon-v1-en2025-08-22
Kimi-Audio Technical Report✓ Link1.28Kimi-Audio2025-04-25
Pulse STT: Fast, Accurate Speech-to-Text1.3smallestai/pulse2026-01-28
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link1.31nvidia/stt_en_fastconformer_transducer_large2023-06-08
Step-Audio 2 Technical Report✓ Link1.33Step-Audio 2 mini2025-08-27
FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information✓ Link1.34FAdam2024-05-21
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs1.35microsoft/Phi-4-multimodal-instruct2025-02-24
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages✓ Link1.35facebook/omniASR-LLM-7B-v22025-12-12
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link1.36facebook/wav2vec2-large-960h-lv60-self2020-06-20
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling✓ Link1.37kyutai/stt-2.6b-en2025-06-06
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language✓ Link1.38facebook/data2vec-audio-large-960h2022-04-02
fairseq S2T: Fast Speech-to-Text Modeling with fairseq✓ Link1.38facebook/wav2vec2-conformer-rel-pos-large-960h-ft2022-04-18
SpeechBrain: A General-Purpose Speech Toolkit✓ Link1.38speechbrain/asr-wav2vec2-librispeech2022-06-05
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition✓ Link1.4Conformer + Wav2vec 2.0 + SpecAugment-based Noisy Student Training with Libri-Light2020-10-20
W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training✓ Link1.4w2v-BERT XXL2021-08-07
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition1.46parakeet-rnnt-1.1b2023-05-08
Voxtral✓ Link1.47mistralai/Voxtral-Mini-3B-25072025-07-01
Data-Efficient On-Policy Distillation for Automatic Speech Recognition✓ Link1.47AutoArk-AI/ARK-ASR-0.6B2026-05-25
Self-training and Pre-training are Complementary for Speech Recognition✓ Link1.5Conv + Transformer + wav2vec2.0 + pseudo labeling2020-10-22
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units✓ Link1.5facebook/hubert-xlarge-ls960-ft2022-03-02
Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST✓ Link1.51nvidia/parakeet-tdt-0.6b-v32025-08-14
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link1.52nvidia/parakeet-ctc-1.1b2023-12-28
Training and Inference Efficiency of Encoder-Decoder Speech Models✓ Link1.52nvidia/canary-180m-flash2025-03-11
fairseq S2T: Fast Speech-to-Text Modeling with fairseq✓ Link1.53facebook/wav2vec2-conformer-rope-large-960h-ft2022-04-18
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units✓ Link1.55facebook/hubert-large-ls960-ft2022-03-02
Robust Speech Recognition via Large-Scale Weak Supervision✓ Link1.55openai/whisper-large-v32023-11-06
VibeVoice-ASR Technical Report✓ Link1.55microsoft/VibeVoice-ASR-HF2026-03-02
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link1.57nvidia/parakeet-ctc-0.6b2023-12-28
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link1.58nvidia/stt_en_fastconformer_ctc_large2023-06-08
Voxtral Realtime✓ Link1.61mistralai/Voxtral-Mini-4B-Realtime-26022026-02-11
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link1.63efficient-speech/lite-whisper-large-v3-acc2025-02-26
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link1.66nvidia/stt_en_conformer_ctc_large2022-04-09
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link1.66efficient-speech/lite-whisper-large-v32025-02-26
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link1.67usefulsensors/moonshine-streaming-medium2026-02-12
Zipformer: A faster and better encoder for automatic speech recognition✓ Link1.67soundsgoodai/Zipformer-transducer-XL-290M2026-05-12
GLM-ASR-Nano: A robust, open-source speech recognition model✓ Link1.69zai-org/GLM-ASR-Nano-25122025-12-09
Qwen3-ASR Technical Report✓ Link1.69Qwen/Qwen3-ASR-0.6B2026-01-28
Improved Noisy Student Training for Automatic Speech Recognition✓ Link1.7ContextNet + SpecAugment-based Noisy Student Training with Libri-Light2020-05-19
SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network1.7SpeechStew (1B)2021-04-05
Ursa 2: Elevating speech recognition across 50+ languages1.73speechmatics/enhanced2024-10-11
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link1.73efficient-speech/lite-whisper-large-v3-turbo-acc2025-02-26
ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition1.75Multistream CNN with Self-Attentive SRU (WER includes text normalization)2020-05-21
Step-Audio 2 Technical Report1.75GPT-4o Transcribe2025-08-27
Multi-Head State Space Model for Speech Recognition1.76Stateformer2023-05-21
Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST✓ Link1.76nvidia/canary-1b-v22025-08-14
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link1.8wav2vec 2.0 with Libri-Light2020-06-20
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units✓ Link1.8HuBERT with Libri-Light2021-06-14
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing✓ Link1.8WavLM Large2021-10-26
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link1.8efficient-speech/lite-whisper-large-v3-fast2025-02-26
E-Branchformer: Branchformer with Enhanced merging for speech recognition✓ Link1.81E-Branchformer (L) + Internal Language Model Estimation2022-09-30
Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use✓ Link1.83speechbrain/asr-conformer-largescaleasr2025-02-06
CR-CTC: Consistency regularization on CTC for improved speech recognition✓ Link1.88Zipformer+pruned transducer w/ CR-CTC (no external language model)2024-10-07
Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition✓ Link1.88nvidia/nemotron-speech-streaming-en-0.6b2026-03-13
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context✓ Link1.9ContextNet(L)2020-05-07
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link1.9Conformer(L)2020-05-16
Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation1.9Transformer+Time reduction+Self Knowledge distillation2021-03-17
OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification✓ Link1.9espnet/owsm_ctc_v3.1_1B2024-02-23
Robust Knowledge Distillation via Large-Scale Pseudo Labelling✓ Link1.93distil-whisper/distil-large-v3.52024-12-05
CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions✓ Link1.99nyrahealth/CrisperWhisper2024-08-29
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context✓ Link2ContextNet(M)2020-05-07
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link2Conformer(M)2020-05-16
Improving RNN Transducer Based ASR with Auxiliary Tasks✓ Link2.0Transformer Transducer2020-11-05
SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network2.0SpeechStew (100M)2021-04-05
Zipformer: A faster and better encoder for automatic speech recognition✓ Link2.00Zipformer+pruned transducer (no external language model)2023-10-17
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models✓ Link2.0Qwen-Audio2023-11-14
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link2.01nvidia/parakeet-tdt_ctc-110m2024-09-17
CR-CTC: Consistency regularization on CTC for improved speech recognition✓ Link2.02Zipformer+CR-CTC (no external language model)2024-10-07
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures✓ Link2.03Conv + Transformer AM + Pseudo-Labeling (ConvLM with Transformer Rescoring)2019-11-19
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link2.07usefulsensors/moonshine-streaming-small2026-02-12
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link2.1Conformer(S)2020-05-16
Iterative Pseudo-Labeling for Speech Recognition✓ Link2.10Conv + Transformer AM + Iterative Pseudo-Labeling (n-gram LM + Transformer Rescoring)2020-05-19
Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces2.10CTC + Transformer LM rescoring2020-05-19
OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning✓ Link2.1espnet/owsm_ctc_v4_1B2025-01-16
Graph Convolutions Enrich the Self-Attention in Transformers!✓ Link2.11Branchformer + GFSA2023-12-07
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages✓ Link2.12facebook/omniASR-CTC-7B-v22025-12-12
Robust Speech Recognition via Large-Scale Weak Supervision✓ Link2.13openai/whisper-large-v3-turbo2024-10-01
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training✓ Link2.16facebook/wav2vec2-large-robust-ft-libri-960h2021-04-02
On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models✓ Link2.17espnet/owsm_ctc_v3.2_ft_1B2024-09-24
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language✓ Link2.19facebook/data2vec-audio-base-960h2022-03-02
State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions✓ Link2.20Multi-Stream Self-Attention With Dilated 1D Convolutions2019-10-01
Librispeech Transducer Model with Internal Language Model Prior Correction✓ Link2.23LSTM Transducer2021-04-07
Transformer-based Acoustic Modeling for Hybrid Speech Recognition2.26Hybrid + Transformer LM rescoring2019-10-22
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation✓ Link2.3Hybrid model with Transformer rescoring2019-05-08
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context✓ Link2.3ContextNet(S)2020-05-07
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures✓ Link2.31Conv + Transformer AM (ConvLM with Transformer Rescoring) (LS only)2019-11-19
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link2.38nvidia/stt_en_conformer_transducer_small2022-06-01
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition✓ Link2.47Squeezeformer (L)2022-06-02
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition✓ Link2.5LAS + SpecAugment2019-04-18
A Comparative Study on Transformer vs RNN in Speech Applications✓ Link2.6Transformer2019-09-13
QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions✓ Link2.69QuartzNet15x52019-10-22
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition✓ Link2.7LAS (no LM)2019-04-18
Self-training and Pre-training are Complementary for Speech Recognition✓ Link2.7wav2vec_wav2letter2020-10-22
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link2.76facebook/wav2vec2-base-960h2022-03-02
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit✓ Link2.8Espresso2019-09-18
Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition✓ Link2.83nvidia/nemotron-3.5-asr-streaming-0.6b2026-06-04
Jasper: An End-to-End Convolutional Neural Acoustic Model✓ Link2.84Jasper DR 10x5 (+ Time/Freq Masks)2019-04-05
Moonshine: Speech Recognition for Live Transcription and Voice Commands✓ Link2.9usefulsensors/moonshine-base2024-10-21
Step-Audio 2 Technical Report2.92Doubao LLM ASR2025-08-27
Step-Audio 2 Technical Report2.93Qwen Omni2025-08-27
Jasper: An End-to-End Convolutional Neural Acoustic Model✓ Link2.95Jasper DR 10x52019-04-05
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link3.03facebook/wav2vec2-large-960h2020-06-20
Neural Network Language Modeling with Letter-based Features and Importance Sampling3.06tdnn + chain + rnnlm rescoring2018-04-15
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link3.12nvidia/stt_en_conformer_ctc_small2023-06-12
Scaling Speech Technology to 1,000+ Languages✓ Link3.14facebook/mms-1b-all2023-05-27
Fully Convolutional Speech Recognition3.26Convolutional Speech Recognition2018-12-17
MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets✓ Link3.4MT4SSL2022-11-14
On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition✓ Link3.60Model Unit Exploration2019-02-05
Niagara-38m Sets a New Benchmark for Edge Speech Recognition3.75abr-ai/niagara-38m-batch.en2026-04-15
Improved training of end-to-end attention models for speech recognition✓ Link3.82Seq-to-seq attention2018-05-08
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link3.98usefulsensors/moonshine-streaming-tiny2026-02-12
Moonshine: Speech Recognition for Live Transcription and Voice Commands✓ Link4.08usefulsensors/moonshine-tiny2024-10-21
CRF-based Single-stage Acoustic Modeling with CTC Topology✓ Link4.09CTC-CRF 4gram-LM2019-04-16
4.3HMM-TDNN trained with MMI + data augmentation (speed) + iVectors + 3 regularizations
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions4.4Centaurus (30 M)2025-01-22
Niagara-38m Sets a New Benchmark for Edge Speech Recognition4.45abr-ai/niagara-19m-batch.en2026-04-15
4.8HMM-TDNN + iVectors
Letter-Based Speech Recognition with Gated ConvNets✓ Link4.8Gated ConvNets2017-12-22
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin✓ Link5.33Deep Speech 22015-12-08
Improving End-to-End Speech Recognition with Policy Learning5.42CTC + policy learning2017-12-19
5.5HMM-DNN + pNorm*
The PyTorch-Kaldi Speech Recognition Toolkit✓ Link6.2Li-GRU2018-11-19
Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces✓ Link6.4Snips2018-05-25
Semi-Supervised Speech Recognition via Local Prior Matching✓ Link7.19Local Prior Matching (Large Model)2020-02-24
8.0HMM-(SAT)GMM
Amortized Neural Networks for Low-Latency Speech Recognition8.6AmNet2021-08-03
Check out how to contribute new results. Then edit this file.