| 1 | AutoArk-AI/ARK-ASR-3B top score | 4.8 (#1) | - | 4063.4M | coming soon |
| 2 | OpenMOSS-Team/MOSS-Transcribe-preview-2B | 4.9 (#2) | - | 2418.8M | coming soon |
| 3 | CohereLabs/cohere-transcribe-03-2026 | 5.4 (#3) | - | 2065.8M | not hosted |
| 4 | AutoArk-AI/ARK-ASR-0.6B | 5.5 (#4) | - | 1299.5M | coming soon |
| 5 | Qwen/Qwen3-ASR-1.7B | 5.8 (#5) | - | 2349.2M | coming soon |
| 6 | microsoft/Phi-4-multimodal-instruct | 6 (#6) | - | 5574.5M | coming soon |
| 7 | nvidia/parakeet-tdt-0.6b-v2 | 6.1 (#7) | - | - | not hosted |
| 8 | nvidia/parakeet-tdt-0.6b-v3 | 6.3 (#8) | - | 627.1M | not hosted |
| 9 | nvidia/canary-1b-flash | 6.4 (#9) | - | 811M | coming soon |
| 10 | kyutai/stt-2.6b-en | 6.4 (#10) | - | 2617.1M | coming soon |
| 11 | Qwen/Qwen3-ASR-0.6B | 6.4 (#11) | - | 938M | coming soon |
| 12 | nvidia/canary-1b | 6.5 (#12) | - | - | not hosted |
| 13 | UsefulSensors/moonshine-streaming-medium | 6.7 (#13) | - | 265.9M | coming soon |
| 14 | soundsgoodai/Zipformer-transducer-XL-290M | 6.7 (#14) | - | - | not hosted |
| 15 | nvidia/parakeet-tdt-1.1b | 7 (#15) | - | - | not hosted |
| 16 | zai-org/GLM-ASR-Nano-2512 | 7 (#16) | - | 2257.8M | coming soon |
| 17 | mistralai/Voxtral-Mini-3B-2507 | 7.1 (#17) | - | 4676.3M | coming soon |
| 18 | nvidia/canary-180m-flash | 7.1 (#18) | - | - | not hosted |
| 19 | nvidia/parakeet-rnnt-1.1b | 7.1 (#19) | - | 1070.5M | coming soon |
| 20 | nvidia/canary-1b-v2 | 7.2 (#20) | - | - | not hosted |
| 21 | distil-whisper/distil-large-v3.5 | 7.2 (#21) | - | 756.4M | coming soon |
| 22 | nvidia/parakeet-ctc-1.1b | 7.4 (#22) | - | 1062.6M | coming soon |
| 23 | espnet/owsm_ctc_v4_1B | 7.4 (#23) | - | - | not hosted |
| 24 | openai/whisper-large-v3 | 7.4 (#24) | - | 1543.5M | not hosted |
| 25 | nvidia/parakeet-tdt_ctc-110m | 7.5 (#25) | - | - | not hosted |
| 26 | nvidia/parakeet-rnnt-0.6b | 7.5 (#26) | - | 616.7M | coming soon |
| 27 | nvidia/parakeet-ctc-0.6b | 7.7 (#27) | - | 608.8M | coming soon |
| 28 | microsoft/VibeVoice-ASR-HF | 7.8 (#28) | - | 8330.3M | coming soon |
| 29 | openai/whisper-large-v2 | 7.8 (#29) | - | 1543.3M | coming soon |
| 30 | UsefulSensors/moonshine-streaming-small | 7.8 (#30) | - | 140.1M | coming soon |
| 31 | openai/whisper-large | 7.9 (#31) | - | 1543.3M | coming soon |
| 32 | openai/whisper-medium.en | 8.1 (#32) | - | 763.9M | coming soon |
| 33 | espnet/owsm_ctc_v3.1_1B | 8.1 (#33) | - | - | not hosted |
| 34 | nvidia/stt_en_conformer_ctc_large | 8.3 (#34) | - | - | not hosted |
| 35 | speechbrain/asr-conformer-loquacious | 8.5 (#35) | - | - | not hosted |
| 36 | openai/whisper-small.en | 8.6 (#36) | - | 241.7M | coming soon |
| 37 | abr-ai/niagara-38m-batch.en | 8.9 (#37) | - | - | not hosted |
| 38 | nvidia/stt_en_fastconformer_ctc_large | 9 (#38) | - | - | not hosted |
| 39 | nvidia/stt_en_fastconformer_transducer_large | 9.1 (#39) | - | - | not hosted |
| 40 | UsefulSensors/moonshine-base | 10 (#40) | - | 61.5M | coming soon |
| 41 | openai/whisper-base.en | 10.3 (#41) | - | 72.6M | coming soon |
| 42 | abr-ai/niagara-19m-batch.en | 10.5 (#42) | - | - | not hosted |
| 43 | nvidia/stt_en_conformer_ctc_small | 11.2 (#43) | - | - | not hosted |
| 44 | UsefulSensors/moonshine-streaming-tiny | 12 (#44) | - | 44.1M | not hosted |
| 45 | UsefulSensors/moonshine-tiny | 12.7 (#45) | - | 27.1M | not hosted |
| 46 | openai/whisper-tiny.en | 12.8 (#46) | - | 37.8M | not hosted |
| 47 | speechbrain/asr-wav2vec2-librispeech | 14.3 (#47) | - | - | not hosted |
| 48 | facebook/wav2vec2-large-960h-lv60-self | 21.3 (#48) | - | - | not hosted |
| 49 | facebook/mms-1b-all | 22.5 (#49) | - | 964.8M | not hosted |
| 50 | facebook/hubert-xlarge-ls960-ft | 22.5 (#50) | - | 962.5M | not hosted |
| 51 | facebook/hubert-large-ls960-ft | 22.7 (#51) | - | - | not hosted |
| 52 | facebook/wav2vec2-large-robust-ft-libri-960h | 22.9 (#52) | - | 315.5M | not hosted |
| 53 | facebook/data2vec-audio-large-960h | 23.2 (#53) | - | - | not hosted |
| 54 | facebook/wav2vec2-conformer-rope-large-960h-ft | 23.3 (#54) | - | 593.4M | not hosted |
| 55 | facebook/wav2vec2-conformer-rel-pos-large-960h-ft | 23.3 (#55) | - | - | not hosted |
| 56 | facebook/wav2vec2-large-960h | 26.8 (#56) | - | - | not hosted |
| 57 | facebook/data2vec-audio-base-960h | 28.3 (#57) | - | - | not hosted |
| 58 | facebook/wav2vec2-base-960h | 29.4 (#58) | - | 94.4M | not hosted |
| 59 | facebook/mms-1b-fl102 | 39.8 (#59) | - | 964.7M | not hosted |
| 60 | pyannote/speaker-diarization-3.1 | - | - | - | coming soon |
| 61 | argmaxinc/whisperkit-coreml | - | - | - | coming soon |
| 62 | openai/whisper-base | - | - | 72.6M | coming soon |
| 63 | jonatasgrosman/wav2vec2-large-xlsr-53-japanese | - | - | - | coming soon |
| 64 | jonatasgrosman/wav2vec2-large-xlsr-53-polish | - | - | - | coming soon |
| 65 | jonatasgrosman/wav2vec2-large-xlsr-53-dutch | - | - | - | coming soon |
| 66 | indonesian-nlp/wav2vec2-indonesian-javanese-sundanese | - | - | - | coming soon |
| 67 | pyannote/speaker-diarization-community-1 | - | - | - | coming soon |
| 68 | jonatasgrosman/wav2vec2-large-xlsr-53-arabic | - | - | - | coming soon |
| 69 | jonatasgrosman/wav2vec2-large-xlsr-53-hungarian | - | - | - | coming soon |
| 70 | openai/whisper-small | - | - | 241.7M | coming soon |
| 71 | MahmoudAshraf/mms-300m-1130-forced-aligner | - | - | 315.5M | coming soon |
| 72 | jonatasgrosman/wav2vec2-large-xlsr-53-portuguese | - | - | - | coming soon |
| 73 | jonatasgrosman/wav2vec2-large-xlsr-53-russian | - | - | - | coming soon |
| 74 | gigant/romanian-wav2vec2 | - | - | 315.5M | coming soon |
| 75 | anuragshas/wav2vec2-large-xlsr-53-telugu | - | - | - | coming soon |
| 76 | jonatasgrosman/wav2vec2-large-xlsr-53-persian | - | - | - | coming soon |
| 77 | KBLab/wav2vec2-large-voxrex-swedish | - | - | 315.5M | coming soon |
| 78 | kingabzpro/wav2vec2-large-xls-r-300m-Urdu | - | - | 315.5M | coming soon |
| 79 | theainerd/Wav2Vec2-large-xlsr-hindi | - | - | 315.5M | coming soon |
