| speech-recognition-on-ami-ihm-open-asr-leaderboard | Granite-speech-4.1-2b | #1 | WER: 8.09 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Granite-4.0-1b-speech | #2 | WER: 8.44 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Granite-speech-3.3-2b | #3 | WER: 8.9 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Canary-qwen-2.5b | #5 | WER: 10.19 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Qwen3-ASR-1.7B | #6 | WER: 10.56 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Moonshine v2 Medium | #7 | WER: 10.68 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Phi-4-multimodal-instruct | #8 | WER: 11.09 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Parakeet-tdt-0.6b-v3 | #9 | WER: 11.39 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | DSM-ASR | #10 | WER: 12.2 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Owsm_ctc_v4_1B | #11 | WER: 13.1 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Canary-1b-flash | #12 | WER: 13.11 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Distil-large-v3.5 | #13 | WER: 14.63 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Distil-large-v2 | #14 | WER: 14.67 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Canary-180m-flash | #15 | WER: 14.86 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Distil-large-v3 | #16 | WER: 15.16 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Voxtral-Small-24B-2507 | #17 | WER: 15.27 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Owsm_ctc_v3.1_1B | #18 | WER: 15.61 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Parakeet-ctc-1.1b | #19 | WER: 15.67 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Parakeet-tdt_ctc-110m | #20 | WER: 15.89 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Stt_en_conformer_ctc_large | #21 | WER: 15.95 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Zipformer-transducer-XL-290M | #22 | WER: 15.97 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Whisper-large-v3-turbo | #23 | WER: 16.13 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | GLM-ASR-Nano-2512 | #24 | WER: 16.15 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Voxtral-Mini-3B-2507 | #25 | WER: 16.3 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Parakeet-ctc-0.6b | #26 | WER: 16.46 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Whisper-medium.en | #27 | WER: 16.68 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Whisper-large | #28 | WER: 16.73 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | VibeVoice-ASR-HF | #29 | WER: 17.2 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Whisper-small.en | #30 | WER: 17.93 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Stt_en_conformer_ctc_small | #31 | WER: 20.43 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Asr-wav2vec2-librispeech | #32 | WER: 32.05 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Wav2vec2-large-960h-lv60-self | #33 | WER: 36.77 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Wav2vec2-large-robust-ft-libri-960h | #34 | WER: 37.75 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Data2vec-audio-large-960h | #35 | WER: 40.51 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Wav2vec2-conformer-rope-large-960h-ft | #36 | WER: 42.47 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Wav2vec2-large-960h | #37 | WER: 42.66 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Wav2vec2-base-960h | #38 | WER: 45.56 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Canary-1b | – | WER: 13.9 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Canary-1b-v2 | – | WER: 16.01 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Cohere-transcribe-03-2026 | – | WER: 8.13 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Moonshine-streaming-medium | – | WER: 10.68 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Moonshine-streaming-small | – | WER: 12.53 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | Moonshine-streaming-tiny | – | WER: 19.02 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | SYMPHONY | – | WER: 10.7 |
| speech-recognition-on-ami-ihm-open-asr-leaderboard | SYMPHONY-ASR | – | WER: 9.56 |
| speech-recognition-on-open-asr-leaderboard | Qwen/Qwen3-ASR-1.7B-hf | #1 | WER: 4.95RTFx: 819.96 |
| speech-recognition-on-open-asr-leaderboard | nvidia/parakeet-tdt-0.6b-v2 | #5 | WER: 5.48RTFx: 6024.67 |
| speech-recognition-on-open-asr-leaderboard | nvidia/parakeet-tdt-0.6b-v3 | #7 | WER: 5.64RTFx: 6172.55 |
| speech-recognition-on-open-asr-leaderboard | Qwen/Qwen3-ASR-0.6B-hf | #9 | WER: 5.7RTFx: 743.96 |
| speech-recognition-on-open-asr-leaderboard | microsoft/Phi-4-multimodal-instruct | #10 | WER: 5.72RTFx: 162.53 |
| speech-recognition-on-open-asr-leaderboard | nvidia/nemotron-speech-streaming-en-0.6b | #13 | WER: 6.0RTFx: 1116.94 |
| speech-recognition-on-open-asr-leaderboard | distil-whisper/distil-large-v3.5 | #15 | WER: 6.2RTFx: 888.33 |
| speech-recognition-on-open-asr-leaderboard | openai/whisper-large-v3 | #18 | WER: 6.5RTFx: 470.21 |
| speech-recognition-on-open-asr-leaderboard | nvidia/parakeet-ctc-1.1b | #19 | WER: 6.65RTFx: 5022.76 |
| speech-recognition-on-open-asr-leaderboard | Moonshine v2 Medium | #20 | WER: 6.65 |
| speech-recognition-on-open-asr-leaderboard | openai/whisper-large-v3-turbo | #21 | WER: 7.03RTFx: 795.43 |
| speech-recognition-on-open-asr-leaderboard | espnet/owsm_ctc_v4_1B | #23 | WER: 7.28RTFx: 776.71 |
| speech-recognition-on-open-asr-leaderboard | mistralai/Voxtral-Mini-4B-Realtime-2602 | #24 | WER: 7.49RTFx: 102.62 |
| speech-recognition-on-open-asr-leaderboard | nvidia/nemotron-3.5-asr-streaming-0.6b | #25 | WER: 8.72RTFx: 1349.06 |
| speech-recognition-on-open-asr-leaderboard | Moonshine Base | #26 | WER: 10.07RTFx: 565.97 |
| speech-recognition-on-open-asr-leaderboard | google/gemma-4-E4B-it | #27 | WER: 10.41RTFx: 161.3 |
| speech-recognition-on-open-asr-leaderboard | CohereLabs/cohere-transcribe-03-2026 | – | WER: 5.4RTFx: 906.56 |
| speech-recognition-on-open-asr-leaderboard | OpenMOSS-Team/MOSS-Transcribe-Diarize | – | WER: 5.52RTFx: 381.16 |
| speech-recognition-on-open-asr-leaderboard | ibm-granite/granite-speech-5.0-470m-turboctc | – | WER: 5.84RTFx: 21222.23 |
| speech-recognition-on-open-asr-leaderboard | nvidia/canary-1b-v2 | – | WER: 6.55RTFx: 1825.15 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Parakeet-rnnt-1.1b | #1 | WER: 5.44 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Parakeet-tdt-1.1b | #2 | WER: 5.49 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Canary-1b-flash | #3 | WER: 5.63 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Canary-qwen-2.5b | #4 | WER: 5.66 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Granite-speech-3.3-2b | #5 | WER: 5.93 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Parakeet-tdt-0.6b-v2 | #6 | WER: 5.95 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Parakeet-tdt-0.6b-v3 | #7 | WER: 6.09 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Canary-180m-flash | #9 | WER: 6.35 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Qwen3-ASR-1.7B | #10 | WER: 6.35 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Parakeet-ctc-1.1b | #11 | WER: 6.56 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Stt-2.6b-en | #12 | WER: 6.79 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | DSM-ASR | #13 | WER: 6.8 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Parakeet-tdt_ctc-110m | #14 | WER: 6.9 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Voxtral-Small-24B-2507 | #15 | WER: 6.96 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Parakeet-ctc-0.6b | #16 | WER: 7.07 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Qwen3-ASR-0.6B | #17 | WER: 7.07 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Distil-large-v3.5 | #18 | WER: 8.04 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Distil-large-v2 | #19 | WER: 8.24 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Distil-large-v3 | #20 | WER: 8.25 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Owsm_ctc_v3.1_1B | #21 | WER: 8.4 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Moonshine v2 Medium | #22 | WER: 8.54 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Whisper-large-v3 | #23 | WER: 9.54 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | CrisperWhisper | #24 | WER: 9.82 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | LFM2-Audio-1.5B | #25 | WER: 9.93 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Mms-1b-all | #26 | WER: 17.63 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Wav2vec2-conformer-rope-large-960h-ft | #27 | WER: 22.61 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Data2vec-audio-large-960h | #28 | WER: 23.86 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Data2vec-audio-base-960h | #29 | WER: 27.25 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Wav2vec2-large-960h | #30 | WER: 30.09 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Wav2vec2-base-960h | #31 | WER: 32.48 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Canary-1b | – | WER: 5.79 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Cohere-transcribe-03-2026 | – | WER: 5.87 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Moonshine-streaming-medium | – | WER: 8.54 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Moonshine-streaming-small | – | WER: 9.98 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Moonshine-streaming-tiny | – | WER: 14.02 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | Niagara-38m-batch.en | – | WER: 8.73 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | SYMPHONY | – | WER: 6.7 |
| speech-recognition-on-voxpopuli-open-asr-leaderboard | SYMPHONY-ASR | – | WER: 6.3 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Qwen3-ASR-1.7B | #2 | WER: 8.74 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Phi-4-multimodal-instruct | #3 | WER: 9.33 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Canary-qwen-2.5b | #4 | WER: 9.43 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Moonshine v2 Medium | #5 | WER: 9.46 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Parakeet-tdt-1.1b | #6 | WER: 9.52 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Parakeet-tdt-0.6b-v3 | #7 | WER: 9.57 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | GLM-ASR-Nano-2512 | #8 | WER: 9.73 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | DSM-ASR | #9 | WER: 9.8 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Granite-speech-4.1-2b | #10 | WER: 9.8 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Distil-large-v3.5 | #11 | WER: 9.84 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Parakeet-rnnt-0.6b | #12 | WER: 10.01 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Distil-large-v3 | #13 | WER: 10.08 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Lite-whisper-large-v3-acc | #14 | WER: 10.1 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Whisper-large-v3-turbo | #15 | WER: 10.14 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Granite-4.0-1b-speech | #16 | WER: 10.14 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Granite-speech-3.3-8b | #17 | WER: 10.19 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Lite-whisper-large-v3-turbo-acc | #18 | WER: 10.21 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Voxtral-Mini-3B-2507 | #19 | WER: 10.24 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Audio Flamingo 3 | #20 | WER: 10.27 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Parakeet-ctc-1.1b | #21 | WER: 10.28 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Distil-large-v2 | #22 | WER: 10.32 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Canary-180m-flash | #23 | WER: 10.51 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | LFM2-Audio-1.5B | #24 | WER: 10.63 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Whisper-large-v2 | #25 | WER: 10.67 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Granite-speech-3.3-2b | #26 | WER: 10.69 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Whisper-large | #27 | WER: 10.76 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Distil-small.en | #28 | WER: 10.87 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Whisper-small.en | #29 | WER: 11.35 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Stt_en_conformer_ctc_large | #30 | WER: 11.6 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Owsm_ctc_v3.1_1B | #31 | WER: 11.88 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Moonshine Base | #32 | WER: 12.19 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Whisper-base.en | #33 | WER: 12.83 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Asr-wav2vec2-librispeech | #34 | WER: 16.92 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Data2vec-audio-large-960h | #35 | WER: 24.8 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Mms-1b-all | #36 | WER: 26.44 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Wav2vec2-base-960h | #37 | WER: 30.85 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Mms-1b-fl102 | #38 | WER: 42.42 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Canary-1b | – | WER: 10.12 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Cohere-transcribe-03-2026 | – | WER: 9.34 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Moonshine-streaming-small | – | WER: 10.4 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Moonshine-streaming-tiny | – | WER: 13.9 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Niagara-19m-batch.en | – | WER: 13.99 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | Niagara-38m-batch.en | – | WER: 12.56 |
| speech-recognition-on-gigaspeech-open-asr-leaderboard | SYMPHONY | – | WER: 12.2 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | VibeVoice-ASR-HF | #2 | WER: 2.57 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Canary-qwen-2.5b | #3 | WER: 2.71 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Parakeet-tdt-0.6b-v3 | #4 | WER: 2.8 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Qwen3-ASR-0.6B | #5 | WER: 2.85 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Phi-4-multimodal-instruct | #6 | WER: 2.94 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Moonshine v2 Medium | #7 | WER: 2.99 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Granite-speech-4.1-2b | #8 | WER: 3.07 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | GLM-ASR-Nano-2512 | #9 | WER: 3.1 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | CrisperWhisper | #10 | WER: 3.2 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Stt-2.6b-en | #11 | WER: 3.35 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Parakeet-tdt-0.6b-v2 | #12 | WER: 3.38 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | DSM-ASR | #13 | WER: 3.4 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Granite-speech-3.3-8b | #14 | WER: 3.4 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Voxtral-Small-24B-2507 | #15 | WER: 3.52 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | LFM2-Audio-1.5B | #16 | WER: 3.56 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Whisper-large-v3-turbo | #17 | WER: 3.57 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Parakeet-ctc-1.1b | #18 | WER: 3.57 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Granite-speech-3.3-2b | #19 | WER: 3.57 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Parakeet-tdt-1.1b | #20 | WER: 3.59 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Distil-large-v3.5 | #21 | WER: 3.64 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Voxtral-Mini-4B-Realtime-2602 | #22 | WER: 3.79 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Parakeet-rnnt-1.1b | #23 | WER: 3.83 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Whisper-large-v3 | #24 | WER: 3.86 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Distil-large-v3 | #25 | WER: 3.86 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Whisper-large | #26 | WER: 3.91 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Whisper-small.en | #27 | WER: 4.07 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Parakeet-tdt_ctc-110m | #28 | WER: 4.07 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Whisper-medium.en | #29 | WER: 4.12 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Zipformer-transducer-XL-290M | #30 | WER: 4.12 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Owsm_ctc_v4_1B | #31 | WER: 4.43 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Distil-small.en | #32 | WER: 4.54 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Distil-medium.en | #33 | WER: 4.84 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Whisper-base.en | #34 | WER: 4.87 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Owsm_ctc_v3.1_1B | #35 | WER: 4.92 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Stt_en_conformer_ctc_small | #36 | WER: 7.16 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Asr-wav2vec2-librispeech | #37 | WER: 7.58 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Wav2vec2-large-960h-lv60-self | #38 | WER: 14.88 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Wav2vec2-conformer-rel-pos-large-960h-ft | #39 | WER: 15.77 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Data2vec-audio-large-960h | #40 | WER: 15.86 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Hubert-large-ls960-ft | #41 | WER: 15.92 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Wav2vec2-conformer-rope-large-960h-ft | #42 | WER: 15.92 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Wav2vec2-large-960h | #43 | WER: 18.85 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Wav2vec2-base-960h | #44 | WER: 21.05 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Asr-conformer-loquacious | – | WER: 4.98 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Canary-1b | – | WER: 3.56 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Cohere-transcribe-03-2026 | – | WER: 2.49 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Moonshine-streaming-medium | – | WER: 2.98 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Moonshine-streaming-small | – | WER: 3.77 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Moonshine-streaming-tiny | – | WER: 6.1 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | Niagara-19m-batch.en | – | WER: 6.73 |
| speech-recognition-on-ted-lium-open-asr-leaderboard | SYMPHONY-ASR | – | WER: 3.39 |
| speech-recognition-on-spgispeech | Audio Flamingo 3 | #5 | Word Error Rate (WER): 1.86 |
| speech-recognition-on-spgispeech | Stt-2.6b-en | #11 | Word Error Rate (WER): 2.03 |
| speech-recognition-on-spgispeech | GLM-ASR-Nano-2512 | #15 | Word Error Rate (WER): 2.08 |
| speech-recognition-on-spgispeech | Distil-large-v3.5 | #37 | Word Error Rate (WER): 2.87 |
| speech-recognition-on-spgispeech | Distil-large-v3 | #43 | Word Error Rate (WER): 3.27 |
| speech-recognition-on-spgispeech | Distil-medium.en | #54 | Word Error Rate (WER): 3.83 |
| speech-recognition-on-spgispeech | LFM2-Audio-1.5B | #56 | Word Error Rate (WER): 4.17 |
| speech-recognition-on-spgispeech | Asr-conformer-loquacious | – | Word Error Rate (WER): 4.11 |
| speech-recognition-on-spgispeech | Canary-1b | – | Word Error Rate (WER): 2.06 |
| speech-recognition-on-spgispeech | Canary-1b-v2 | – | Word Error Rate (WER): 2.28 |
| speech-recognition-on-spgispeech | Cohere-transcribe-03-2026 | – | Word Error Rate (WER): 3.08 |
| speech-recognition-on-spgispeech | Moonshine-streaming-medium | – | Word Error Rate (WER): 2.58 |
| speech-recognition-on-spgispeech | Moonshine-streaming-tiny | – | Word Error Rate (WER): 6.16 |
| speech-recognition-on-spgispeech | Niagara-19m-batch.en | – | Word Error Rate (WER): 3.77 |
| speech-recognition-on-spgispeech | SYMPHONY | – | Word Error Rate (WER): 2.32 |
| speech-recognition-on-spgispeech | SYMPHONY-ASR | – | Word Error Rate (WER): 2.29 |
| speech-recognition-on-earnings-22 | GLM-ASR-Nano-2512 | #23 | Word Error Rate (WER): 11.08 |
| speech-recognition-on-earnings-22 | Distil-large-v3 | #31 | Word Error Rate (WER): 11.79 |
| speech-recognition-on-earnings-22 | Distil-medium.en | #42 | Word Error Rate (WER): 12.99 |
| speech-recognition-on-earnings-22 | Distil-small.en | #44 | Word Error Rate (WER): 13.15 |
| speech-recognition-on-earnings-22 | Canary-1b | – | Word Error Rate (WER): 12.19 |
| speech-recognition-on-earnings-22 | Canary-1b-v2 | – | Word Error Rate (WER): 11.79 |
| speech-recognition-on-earnings-22 | Moonshine-streaming-medium | – | Word Error Rate (WER): 11.92 |
| speech-recognition-on-earnings-22 | Moonshine-streaming-small | – | Word Error Rate (WER): 13.55 |
| speech-recognition-on-earnings-22 | Niagara-38m-batch.en | – | Word Error Rate (WER): 12.09 |
| speech-recognition-on-earnings-22 | SYMPHONY | – | Word Error Rate (WER): 9.92 |
| speech-recognition-on-earnings-22 | SYMPHONY-ASR | – | Word Error Rate (WER): 9.45 |
| speech-recognition-on-librispeech-test-other | Llama 3 Speech (70B) | #30 | Word Error Rate (WER): 3.1 |
| speech-recognition-on-librispeech-test-other | Audio Flamingo 3 | #32 | Word Error Rate (WER): 3.13 |
| speech-recognition-on-librispeech-test-other | Qwen2-Audio | #50 | Word Error Rate (WER): 3.6 |
| speech-recognition-on-librispeech-test-other | Stt-2.6b-en | #74 | Word Error Rate (WER): 4.32 |
| speech-recognition-on-librispeech-test-other | LFM2-Audio-1.5B | #79 | Word Error Rate (WER): 4.39 |
| speech-recognition-on-librispeech-test-other | GLM-ASR-Nano-2512 | #80 | Word Error Rate (WER): 4.42 |
| speech-recognition-on-librispeech-test-other | Distil-large-v3.5 | #96 | Word Error Rate (WER): 5.04 |
| speech-recognition-on-librispeech-test-other | Owsm_ctc_v3.1_1B | #98 | Word Error Rate (WER): 5.15 |
| speech-recognition-on-librispeech-test-other | Distil-large-v3 | #100 | Word Error Rate (WER): 5.19 |
| speech-recognition-on-librispeech-test-other | Distil-large-v2 | #117 | Word Error Rate (WER): 6.84 |
| speech-recognition-on-librispeech-test-other | Distil-medium.en | #125 | Word Error Rate (WER): 8.35 |
| speech-recognition-on-librispeech-test-other | Asr-conformer-loquacious | – | Word Error Rate (WER): 4.24 |
| speech-recognition-on-librispeech-test-other | Canary-1b | – | Word Error Rate (WER): 2.93 |
| speech-recognition-on-librispeech-test-other | Canary-1b-v2 | – | Word Error Rate (WER): 3.56 |
| speech-recognition-on-librispeech-test-other | Moonshine-streaming-small | – | Word Error Rate (WER): 6.78 |
| speech-recognition-on-librispeech-test-other | Moonshine-streaming-tiny | – | Word Error Rate (WER): 12.1 |
| speech-recognition-on-librispeech-test-other | Qwen3.5-Omni-Plus | – | Word Error Rate (WER): 2.23 |
| speech-recognition-on-librispeech-test-other | SYMPHONY | – | Word Error Rate (WER): 4.48 |
| speech-recognition-on-librispeech-test-other | SYMPHONY-ASR | – | Word Error Rate (WER): 4.43 |
| speech-recognition-on-librispeech-test-clean | Audio Flamingo 3 | #43 | Word Error Rate (WER): 1.57 |
| speech-recognition-on-librispeech-test-clean | Qwen2-Audio | #45 | Word Error Rate (WER): 1.6 |
| speech-recognition-on-librispeech-test-clean | Stt-2.6b-en | #56 | Word Error Rate (WER): 1.7 |
| speech-recognition-on-librispeech-test-clean | LFM2-Audio-1.5B | #80 | Word Error Rate (WER): 2.03 |
| speech-recognition-on-librispeech-test-clean | GLM-ASR-Nano-2512 | #89 | Word Error Rate (WER): 2.15 |
| speech-recognition-on-librispeech-test-clean | Distil-large-v3.5 | #99 | Word Error Rate (WER): 2.37 |
| speech-recognition-on-librispeech-test-clean | Distil-large-v2 | #114 | Word Error Rate (WER): 2.94 |
| speech-recognition-on-librispeech-test-clean | Moshi ASR | #128 | Word Error Rate (WER): 5.7 |
| speech-recognition-on-librispeech-test-clean | Asr-conformer-loquacious | – | Word Error Rate (WER): 1.95 |
| speech-recognition-on-librispeech-test-clean | Canary-1b | – | Word Error Rate (WER): 1.48 |
| speech-recognition-on-librispeech-test-clean | Canary-1b-v2 | – | Word Error Rate (WER): 2.18 |
| speech-recognition-on-librispeech-test-clean | Cohere-transcribe-03-2026 | – | Word Error Rate (WER): 1.25 |
| speech-recognition-on-librispeech-test-clean | Moonshine-streaming-medium | – | Word Error Rate (WER): 2.09 |
| speech-recognition-on-librispeech-test-clean | Moonshine-streaming-small | – | Word Error Rate (WER): 2.49 |
| speech-recognition-on-librispeech-test-clean | Niagara-19m-batch.en | – | Word Error Rate (WER): 4.81 |
| speech-recognition-on-librispeech-test-clean | Niagara-38m-batch.en | – | Word Error Rate (WER): 3.84 |
| speech-recognition-on-librispeech-test-clean | Qwen3.5-Omni-Plus | – | Word Error Rate (WER): 1.11 |
| speech-recognition-on-librispeech-test-clean | SYMPHONY | – | Word Error Rate (WER): 1.95 |
| speech-recognition-on-librispeech-test-clean | SYMPHONY-ASR | – | Word Error Rate (WER): 1.91 |