OpenCodePapers

speech-recognition-on-voxpopuli-cleaned

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 Scribe v21.41elevenlabs/scribe_v22026-01-09
Introducing Universal-3 Pro: A new class of speech language model optimized for Voice AI1.83assemblyai/universal-3-pro2026-02-03
Avalon: ASR for Human–AI Interaction1.86aquavoice/avalon-v1-en2025-08-22
Voxtral✓ Link2mistralai/Voxtral-Small-24B-25072025-07-15
VibeVoice-ASR Technical Report✓ Link2.02microsoft/VibeVoice-ASR-HF2026-03-02
GLM-ASR-Nano: A robust, open-source speech recognition model✓ Link2.05zai-org/GLM-ASR-Nano-25122025-12-09
Introducing Resonant-1 and Resonant-1-flash2.19reson8/resonant-12026-04-08
Introducing Resonant-1 and Resonant-1-flash2.19reson8/resonant-1-flash2026-04-08
Voxtral✓ Link2.22mistralai/Voxtral-Mini-3B-25072025-07-01
Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition✓ Link2.4nvidia/nemotron-speech-streaming-en-0.6b2026-03-13
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link2.5efficient-speech/lite-whisper-large-v32025-02-26
Robust Knowledge Distillation via Large-Scale Pseudo Labelling✓ Link2.52distil-whisper/distil-large-v3.52024-12-05
Voxtral Realtime✓ Link2.6mistralai/Voxtral-Mini-4B-Realtime-26022026-02-11
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link2.65efficient-speech/lite-whisper-large-v3-fast2025-02-26
Data-Efficient On-Policy Distillation for Automatic Speech Recognition✓ Link2.76AutoArk-AI/ARK-ASR-0.6B2026-05-25
Ursa 2: Elevating speech recognition across 50+ languages2.83speechmatics/enhanced2024-10-11
Boson AI Launches Higgs STT 3 Speech-to-Text Model✓ Link2.94bosonai/higgs-audio-v3-8b-stt-v22026-04-27
Qwen3-ASR Technical Report✓ Link3.01Qwen/Qwen3-ASR-1.7B2026-01-28
Qwen3-ASR Technical Report✓ Link3.07Qwen/Qwen3-ASR-0.6B2026-01-28
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link3.19nvidia/parakeet-ctc-0.6b2023-12-28
Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST✓ Link3.19nvidia/parakeet-tdt-0.6b-v32025-08-14
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link3.24nvidia/parakeet-ctc-1.1b2023-12-28
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link3.35efficient-speech/lite-whisper-large-v3-acc2025-02-26
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link3.35efficient-speech/lite-whisper-large-v3-turbo-acc2025-02-26
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link3.37usefulsensors/moonshine-streaming-medium2026-02-12
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link3.41nvidia/parakeet-rnnt-0.6b2023-12-28
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling✓ Link3.53kyutai/stt-2.6b-en2025-06-06
Data-Efficient On-Policy Distillation for Automatic Speech Recognition✓ Link3.55AutoArk-AI/ARK-ASR-3B2026-06-22
Training and Inference Efficiency of Encoder-Decoder Speech Models✓ Link3.57nvidia/canary-180m-flash2025-03-11
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link3.62nvidia/parakeet-tdt-1.1b2024-01-25
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link3.64nvidia/parakeet-rnnt-1.1b2023-12-27
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link3.72nvidia/parakeet-tdt_ctc-110m2024-09-17
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link3.73nvidia/stt_en_conformer_ctc_large2022-04-09
Boson AI Launches Higgs STT 3 Speech-to-Text Model✓ Link3.73bosonai/higgs-audio-v3-stt2026-03-18
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link3.76usefulsensors/moonshine-streaming-small2026-02-12
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link3.77nvidia/stt_en_fastconformer_ctc_large2023-06-08
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link3.78nvidia/parakeet-tdt-0.6b-v22025-05-01
Pulse STT: Fast, Accurate Speech-to-Text3.85smallestai/pulse2026-01-28
Azure Speech at Build 2026: Powering Voice Agents with Real-Time and Life-like Experiences3.87microsoft/azure-speech-06-20262026-06-04
Introducing Zoom AI Services3.95zoom/scribe_v12026-03-10
Less is More: Accurate Speech Recognition & Translation without Web-Scale Data✓ Link4.01nvidia/canary-1b2024-02-07
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages✓ Link4.03facebook/omniASR-LLM-7B-v22025-12-12
Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use✓ Link4.06speechbrain/asr-conformer-largescaleasr2025-02-06
Zipformer: A faster and better encoder for automatic speech recognition✓ Link4.08soundsgoodai/Zipformer-transducer-XL-290M2026-05-12
OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning✓ Link4.09espnet/owsm_ctc_v4_1B2025-01-16
✓ Link4.14nvidia/canary-qwen-2.5b2025-07-17
Training and Inference Efficiency of Encoder-Decoder Speech Models✓ Link4.17nvidia/canary-1b-flash2025-03-07
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs4.18microsoft/Phi-4-multimodal-instruct2025-02-24
✓ Link4.18ibm-granite/granite-speech-4.1-2b2026-04-29
Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition✓ Link4.24nvidia/nemotron-3.5-asr-streaming-0.6b2026-06-04
NLE: Non-autoregressive LLM-based ASR by Transcript Editing✓ Link4.25ibm-granite/granite-speech-4.1-2b-nar2026-04-01
CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions✓ Link4.27nyrahealth/CrisperWhisper2024-08-29
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link4.29nvidia/stt_en_conformer_transducer_small2022-06-01
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link4.31nvidia/stt_en_fastconformer_transducer_large2023-06-08
Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST✓ Link4.39nvidia/canary-1b-v22025-08-14
Moonshine: Speech Recognition for Live Transcription and Voice Commands✓ Link4.41usefulsensors/moonshine-base2024-10-21
✓ Link4.41ibm-granite/granite-4.0-1b-speech2026-03-06
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages✓ Link4.43facebook/omniASR-CTC-7B-v22025-12-12
On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models✓ Link4.45espnet/owsm_ctc_v3.2_ft_1B2024-09-24
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities✓ Link4.52ibm-granite/granite-speech-3.3-2b2025-06-19
Robust Speech Recognition via Large-Scale Weak Supervision✓ Link4.53openai/whisper-large-v32023-11-06
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities✓ Link4.54ibm-granite/granite-speech-3.3-8b2025-06-19
OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification✓ Link4.58espnet/owsm_ctc_v3.1_1B2024-02-23
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link4.6nvidia/stt_en_conformer_ctc_small2023-06-12
4.88OpenMOSS-Team/MOSS-Transcribe-preview-2B2026-06-26
Scaling Speech Technology to 1,000+ Languages✓ Link5.1facebook/mms-1b-all2023-05-27
Niagara-38m Sets a New Benchmark for Edge Speech Recognition5.16abr-ai/niagara-38m-batch.en2026-04-15
Introducing Cohere-transcribe: state-of-the-art speech recognition5.38CohereLabs/cohere-transcribe-03-20262026-03-26
Niagara-38m Sets a New Benchmark for Edge Speech Recognition5.93abr-ai/niagara-19m-batch.en2026-04-15
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link6.27facebook/wav2vec2-large-960h-lv60-self2020-06-20
Moonshine: Speech Recognition for Live Transcription and Voice Commands✓ Link6.52usefulsensors/moonshine-tiny2024-10-21
fairseq S2T: Fast Speech-to-Text Modeling with fairseq✓ Link6.71facebook/wav2vec2-conformer-rope-large-960h-ft2022-04-18
SpeechBrain: A General-Purpose Speech Toolkit✓ Link6.81speechbrain/asr-wav2vec2-librispeech2022-06-05
fairseq S2T: Fast Speech-to-Text Modeling with fairseq✓ Link6.88facebook/wav2vec2-conformer-rel-pos-large-960h-ft2022-04-18
Robust Speech Recognition via Large-Scale Weak Supervision✓ Link7.02openai/whisper-large-v3-turbo2024-10-01
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language✓ Link7.13facebook/data2vec-audio-large-960h2022-04-02
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units✓ Link7.33facebook/hubert-xlarge-ls960-ft2022-03-02
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units✓ Link7.78facebook/hubert-large-ls960-ft2022-03-02
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link8.11usefulsensors/moonshine-streaming-tiny2026-02-12
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training✓ Link8.21facebook/wav2vec2-large-robust-ft-libri-960h2021-04-02
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language✓ Link12.76facebook/data2vec-audio-base-960h2022-03-02
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link12.87facebook/wav2vec2-large-960h2020-06-20
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link15.16facebook/wav2vec2-base-960h2022-03-02
Check out how to contribute new results. Then edit this file.