OpenCodePapers

speech-recognition-on-gigaspeech-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
6.69OpenMOSS-Team/MOSS-Transcribe-preview-2B2026-06-26
Data-Efficient On-Policy Distillation for Automatic Speech Recognition✓ Link6.94AutoArk-AI/ARK-ASR-3B2026-06-22
Boson AI Launches Higgs STT 3 Speech-to-Text Model✓ Link7.09bosonai/higgs-audio-v3-8b-stt-v22026-04-27
Qwen3-ASR Technical Report✓ Link7.22Qwen/Qwen3-ASR-1.7B2026-01-28
Azure Speech at Build 2026: Powering Voice Agents with Real-Time and Life-like Experiences7.26microsoft/azure-speech-06-20262026-06-04
Data-Efficient On-Policy Distillation for Automatic Speech Recognition✓ Link7.38AutoArk-AI/ARK-ASR-0.6B2026-05-25
Introducing Resonant-1 and Resonant-1-flash7.39reson8/resonant-12026-04-08
Introducing Resonant-1 and Resonant-1-flash7.39reson8/resonant-1-flash2026-04-08
Boson AI Launches Higgs STT 3 Speech-to-Text Model✓ Link7.45bosonai/higgs-audio-v3-stt2026-03-18
Introducing Universal-3 Pro: A new class of speech language model optimized for Voice AI7.54assemblyai/universal-3-pro2026-02-03
Qwen3-ASR Technical Report✓ Link7.62Qwen/Qwen3-ASR-0.6B2026-01-28
Introducing Scribe v27.64elevenlabs/scribe_v22026-01-09
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs7.8microsoft/Phi-4-multimodal-instruct2025-02-24
✓ Link7.81nvidia/canary-qwen-2.5b2025-07-17
Ursa 2: Elevating speech recognition across 50+ languages7.84speechmatics/enhanced2024-10-11
VibeVoice-ASR Technical Report✓ Link7.87microsoft/VibeVoice-ASR-HF2026-03-02
Introducing Zoom AI Services7.87zoom/scribe_v12026-03-10
Introducing Cohere-transcribe: state-of-the-art speech recognition7.88CohereLabs/cohere-transcribe-03-20262026-03-26
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link7.9nvidia/parakeet-tdt-1.1b2024-01-25
Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition✓ Link7.91nvidia/nemotron-speech-streaming-en-0.6b2026-03-13
Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST✓ Link8nvidia/parakeet-tdt-0.6b-v32025-08-14
GLM-ASR-Nano: A robust, open-source speech recognition model✓ Link8.02zai-org/GLM-ASR-Nano-25122025-12-09
Avalon: ASR for Human–AI Interaction8.03aquavoice/avalon-v1-en2025-08-22
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link8.1usefulsensors/moonshine-streaming-medium2026-02-12
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link8.15nvidia/parakeet-tdt-0.6b-v22025-05-01
Pulse STT: Fast, Accurate Speech-to-Text8.18smallestai/pulse2026-01-28
✓ Link8.18ibm-granite/granite-speech-4.1-2b2026-04-29
Training and Inference Efficiency of Encoder-Decoder Speech Models✓ Link8.19nvidia/canary-1b-flash2025-03-07
Robust Knowledge Distillation via Large-Scale Pseudo Labelling✓ Link8.21distil-whisper/distil-large-v3.52024-12-05
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link8.22nvidia/parakeet-rnnt-1.1b2023-12-27
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling✓ Link8.22kyutai/stt-2.6b-en2025-06-06
Voxtral✓ Link8.33mistralai/Voxtral-Small-24B-25072025-07-15
Robust Speech Recognition via Large-Scale Weak Supervision✓ Link8.35openai/whisper-large-v32023-11-06
✓ Link8.44ibm-granite/granite-4.0-1b-speech2026-03-06
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link8.45nvidia/parakeet-rnnt-0.6b2023-12-28
Less is More: Accurate Speech Recognition & Translation without Web-Scale Data✓ Link8.47nvidia/canary-1b2024-02-07
Robust Speech Recognition via Large-Scale Weak Supervision✓ Link8.47openai/whisper-large-v3-turbo2024-10-01
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link8.48efficient-speech/lite-whisper-large-v3-acc2025-02-26
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities✓ Link8.58ibm-granite/granite-speech-3.3-8b2025-06-19
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link8.59efficient-speech/lite-whisper-large-v3-turbo-acc2025-02-26
CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions✓ Link8.62nyrahealth/CrisperWhisper2024-08-29
NLE: Non-autoregressive LLM-based ASR by Transcript Editing✓ Link8.62ibm-granite/granite-speech-4.1-2b-nar2026-04-01
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link8.64efficient-speech/lite-whisper-large-v32025-02-26
Voxtral✓ Link8.7mistralai/Voxtral-Mini-3B-25072025-07-01
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link8.74nvidia/parakeet-ctc-1.1b2023-12-28
Voxtral Realtime✓ Link8.8mistralai/Voxtral-Mini-4B-Realtime-26022026-02-11
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations✓ Link8.84nvidia/parakeet-tdt_ctc-110m2024-09-17
Training and Inference Efficiency of Encoder-Decoder Speech Models✓ Link8.87nvidia/canary-180m-flash2025-03-11
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link8.9nvidia/parakeet-ctc-0.6b2023-12-28
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation✓ Link9.02efficient-speech/lite-whisper-large-v3-fast2025-02-26
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities✓ Link9.03ibm-granite/granite-speech-3.3-2b2025-06-19
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link9.03usefulsensors/moonshine-streaming-small2026-02-12
Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST✓ Link9.12nvidia/canary-1b-v22025-08-14
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages✓ Link9.21facebook/omniASR-LLM-7B-v22025-12-12
Zipformer: A faster and better encoder for automatic speech recognition✓ Link9.21soundsgoodai/Zipformer-transducer-XL-290M2026-05-12
OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning✓ Link9.29espnet/owsm_ctc_v4_1B2025-01-16
Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use✓ Link9.7speechbrain/asr-conformer-largescaleasr2025-02-06
Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition✓ Link9.86nvidia/nemotron-3.5-asr-streaming-0.6b2026-06-04
On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models✓ Link10.14espnet/owsm_ctc_v3.2_ft_1B2024-09-24
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link10.18nvidia/stt_en_conformer_ctc_large2022-04-09
OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification✓ Link10.35espnet/owsm_ctc_v3.1_1B2024-02-23
Moonshine: Speech Recognition for Live Transcription and Voice Commands✓ Link10.58usefulsensors/moonshine-base2024-10-21
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link10.67nvidia/stt_en_fastconformer_transducer_large2023-06-08
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition✓ Link10.89nvidia/stt_en_fastconformer_ctc_large2023-06-08
Niagara-38m Sets a New Benchmark for Edge Speech Recognition11.31abr-ai/niagara-38m-batch.en2026-04-15
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link12.26nvidia/stt_en_conformer_transducer_small2022-06-01
Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications✓ Link12.46usefulsensors/moonshine-streaming-tiny2026-02-12
Moonshine: Speech Recognition for Live Transcription and Voice Commands✓ Link12.6usefulsensors/moonshine-tiny2024-10-21
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages✓ Link12.95facebook/omniASR-CTC-7B-v22025-12-12
Conformer: Convolution-augmented Transformer for Speech Recognition✓ Link13.17nvidia/stt_en_conformer_ctc_small2023-06-12
Niagara-38m Sets a New Benchmark for Edge Speech Recognition14.07abr-ai/niagara-19m-batch.en2026-04-15
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link14.76facebook/wav2vec2-large-960h-lv60-self2020-06-20
SpeechBrain: A General-Purpose Speech Toolkit✓ Link15.07speechbrain/asr-wav2vec2-librispeech2022-06-05
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language✓ Link15.68facebook/data2vec-audio-large-960h2022-04-02
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units✓ Link15.77facebook/hubert-xlarge-ls960-ft2022-03-02
fairseq S2T: Fast Speech-to-Text Modeling with fairseq✓ Link15.87facebook/wav2vec2-conformer-rel-pos-large-960h-ft2022-04-18
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units✓ Link16.02facebook/hubert-large-ls960-ft2022-03-02
fairseq S2T: Fast Speech-to-Text Modeling with fairseq✓ Link16.03facebook/wav2vec2-conformer-rope-large-960h-ft2022-04-18
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training✓ Link16.3facebook/wav2vec2-large-robust-ft-libri-960h2021-04-02
Scaling Speech Technology to 1,000+ Languages✓ Link17.15facebook/mms-1b-all2023-05-27
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link19.09facebook/wav2vec2-large-960h2020-06-20
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language✓ Link21.39facebook/data2vec-audio-base-960h2022-03-02
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations✓ Link22.3facebook/wav2vec2-base-960h2022-03-02
Check out how to contribute new results. Then edit this file.