| 1 | FireRedLID-vllm | — | PatchyTisa | 92.07 | medium | CommonVoice test |
| 2 | FireRedASR2-LLM-vllm | — | allendou | 92.07 | medium | CommonVoice test |
| 3 | FireRedLID | FireRedTeam/FireRedLID | FireRedTeam | 92.07 | medium | CommonVoice test |
| 4 | FireRedPunc | FireRedTeam/FireRedPunc | FireRedTeam | 92.07 | medium | CommonVoice test |
| 5 | whisper-small-cantonese | openai/whisper-small | alvanlii | 85.0 | medium | Common Voice 16.0 yue Train |
| 6 | CrisperWhisper | openai/whisper-large-v3 | nyralabs | 80.0 | medium | [Common Voice](https://commonvoice.mozilla.org/en/datasets) |
| 7 | CrisperWhisper | openai/whisper-large-v3 | unsloth | 80.0 | medium | [Common Voice](https://commonvoice.mozilla.org/en/datasets) |
| 8 | MERaLiON-3-10B | openai/whisper-large-v3 | MERaLiON | 76.84 | medium | Age (commonvoice-en, ta, th, vi, zh) |
| 9 | code-switched-egyptian-arabic-whisper-small | openai/whisper-small | IbrahimAmin | 74.16 | medium | Common Voice 17.0 Arabic Subset (Test Set) |
| 10 | whisper-small-malayalam | openai/whisper-small | sajilck | 70.7 | medium | CommonVoice |
| 11 | kb-whisper-large | openai/whisper-large-v3 | KBLab | 67.8 | high | |
| 12 | kb-whisper-base | openai/whisper-base | KBLab | 67.8 | high | |
| 13 | kb-whisper-small | openai/whisper-small | KBLab | 67.8 | high | |
| 14 | kb-whisper-tiny | openai/whisper-tiny | KBLab | 67.8 | high | |
| 15 | kb-whisper-medium | openai/whisper-medium | KBLab | 67.8 | high | |
| 16 | MERaLiON-3-10B | openai/whisper-large-v3 | MERaLiON | 64.86 | medium | Commonvoice |
| 17 | whisper-large-v3-turbo-cantonese-yue-english | openai/whisper-large-v3-turbo | JackyHoCL | 64.0 | medium | mozilla-foundation/common_voice_17_0 |
| 18 | Whisper-Hindi2Hinglish-Prime | openai/whisper-large-v3 | Oriserve | 61.94 | medium | [Common-Voice](https://commonvoice.mozilla.org/en) |
| 19 | Whisper-Hindi2Hinglish-Apex | openai/whisper-large-v3-turbo | Oriserve | 61.94 | medium | [Common-Voice](https://commonvoice.mozilla.org/en) |
| 20 | swecha-gonthuka-asr | Harveenchadha/wav2vec2-pretrained-clsril-23-10k | swechatelangana | 58.0 | medium | Common Voice 22 (te) |
| 21 | MERaLiON-3-10B | openai/whisper-large-v3 | MERaLiON | 45.2 | medium | commonvoice |
| 22 | Whisper-Hindi2Hinglish-Swift | openai/whisper-base | Oriserve | 38.65 | medium | [Common-Voice](https://commonvoice.mozilla.org/en) |
| 23 | whisper-large-v3-turbo-lt | openai/whisper-large-v3-turbo | svogunas | 32.93 | medium | **Common Voice 17 lt** (test, n=4 753) |
| 24 | whisper-small-hu | openai/whisper-small | SubZtep | 26.0 | medium | |
| 25 | nemotron-3.5-asr-streaming-slovenian | nvidia/nemotron-3.5-asr-streaming-0.6b | texdata | 25.07 | medium | Common Voice sl |
| 26 | whisper-small-malayalam | openai/whisper-small | sajilck | 25.0 | medium | |
| 27 | whisper-tiny_ro-80mel | openai/whisper-tiny | IonGrozea | 25.0 | medium | |
| 28 | whisper-base_ro-80mel | openai/whisper-base | IonGrozea | 25.0 | medium | |
| 29 | whisper-medium_ro-80mel | openai/whisper-medium | IonGrozea | 25.0 | medium | |
| 30 | whisper-small_ro-80mel | openai/whisper-small | IonGrozea | 25.0 | medium | |
| 31 | hviske-v5 | — | syvai | 24.3 | medium | Common Voice 17 |
| 32 | whisper-small-sr | openai/whisper-small | istomin9192 | 24.0 | medium | |
| 33 | wav2vec2-large-mms-1b-hungarian | facebook/mms-1b-all | GaborMadarasz | 24.0 | medium | |
| 34 | japanese-wav2vec2-base-rs35kh | reazon-research/japanese-wav2vec2-base | reazon-research | 23.76 | high | TEDxJP-10K⬇ |
| 35 | wav2vec2-large-xlsr-53-th | — | airesearch | 23.04 | medium | [Kaldi from scratch](https://github.com/vistec-AI/commonvoice-th) |
| 36 | whisper-small-tr | openai/whisper-small | ogulcanakca | 23.0 | medium | |
| 37 | SraVaani-1.0 | — | ARTPARK-IISc | 22.6 | low | |
| 38 | swecha-gonthuka-asr | Harveenchadha/wav2vec2-pretrained-clsril-23-10k | swechatelangana | 22.0 | medium | |
| 39 | moonshine-tiny-de-fidoriel-GGUF | fidoriel/moonshine-tiny-de | cstr | 22.0 | medium | |
| 40 | moonshine-base-de-fidoriel-GGUF | fidoriel/moonshine-base-de | cstr | 22.0 | medium | |
| 41 | Qwen3-ASR-1.7B-NL | Qwen/Qwen3-ASR-1.7B | yuriyvnv | 22.0 | medium | |
| 42 | F5-TTS-Romanian | SWivid/F5-TTS | MihaiPopa-1 | 22.0 | medium | |
| 43 | whisper-medium-uzbek | openai/whisper-medium | navai-uz | 22.0 | medium | |
| 44 | whisper-large-v3-turbo-russian | openai/whisper-large-v3-turbo | coriollon | 21.0 | medium | |
| 45 | ipa-whisper-medium | openai/whisper-medium | neurlang | 21.0 | medium | |
| 46 | ipa-whisper-base | openai/whisper-base | neurlang | 21.0 | medium | |
| 47 | whisper-large-v3-turbo-russian-codeswitch | coriollon/whisper-large-v3-turbo-russian | coriollon | 21.0 | medium | |
| 48 | heep-indic | — | bc7ec356 | 21.0 | medium | CommonVoice |
| 49 | whisper-small-persian-v1 | openai/whisper-small | aliyzd95 | 21.0 | medium | |
| 50 | indic_whisper_nodcil | — | parthiv11 | 20.8 | low | |
| 51 | heep-indic | — | bc7ec356 | 20.8 | low | |
| 52 | wav2vec2-xls-r-300m-ftspeech | facebook/wav2vec2-xls-r-300m | saattrupdan | 20.48 | medium | [Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train) |
| 53 | whisper-large-v3-swahili-afrivoice-cv | openai/whisper-large-v3 | ElizabethMwangi | 20.1 | medium | CommonVoice Swahili test |
| 54 | whisper-ja-anime-v0.3 | — | efwkjn | 20.0 | medium | |
| 55 | whisper-base-armenian | openai/whisper-base | Chillarmo | 20.0 | medium | |
| 56 | whisper-ja-1.5B | efwkjn/whisper-ja-1.5B | efwkjn | 20.0 | medium | |
| 57 | whisper-ja-1.5B-ct2 | efwkjn/whisper-ja-1.5B | TransWithAI | 20.0 | medium | |
| 58 | ATOM | — | Chillarmo | 20.0 | medium | |
| 59 | whisper-small-mn | openai/whisper-small | Blgn94 | 20.0 | medium | |
| 60 | RE-USE | nvidia/RE-USE | nvidia | 19.0 | medium | |
| 61 | parakeet-primeline | — | primeline | 19.0 | medium | |
| 62 | T-one | — | t-tech | 19.0 | medium | |
| 63 | Real-time_RE-USE | nvidia/Real-time_RE-USE | nvidia | 19.0 | medium | |
| 64 | TEA-ASR-1.1 | Qwen/Qwen3-ASR-1.7B | JacobLinCool | 19.0 | medium | |
| 65 | TEA-ASR-1 | Qwen/Qwen3-ASR-1.7B | JacobLinCool | 19.0 | medium | |
| 66 | whisper-large-v3-lv-late-cv19 | openai/whisper-large-v3 | AiLab-IMCS-UL | 19.0 | medium | |
| 67 | TEA-ASR-1.1-mini | Qwen/Qwen3-ASR-0.6B | JacobLinCool | 19.0 | medium | |
| 68 | wav2vec2-base-vietnamese-250h | facebook/wav2vec2-base | nguyenvulebinh | 18.34 | low | |
| 69 | japanese-wav2vec2-large-rs35kh | reazon-research/japanese-wav2vec2-large | reazon-research | 18.23 | high | TEDxJP-10K⬇ |
| 70 | whisper-large-v3-eu | openai/whisper-large-v3 | xezpeleta | 18.0 | medium | |
| 71 | whisper-large-v3-hu | openai/whisper-large-v3 | Trendency | 18.0 | medium | |
| 72 | asr-conformer-loquacious | — | speechbrain | 18.0 | medium | |
| 73 | cohere-transcribe-03-2026 | CohereLabs/cohere-transcribe-03-2026 | CohereLabs | 17.0 | medium | |
| 74 | cohere-transcribe-03-2026-gguf | CohereLabs/cohere-transcribe-03-2026 | handy-computer | 17.0 | medium | |
| 75 | csm-1b-danish-tts | sesame/csm-1b | nicolajreck | 17.0 | medium | |
| 76 | whisper-large-v3-russian | antony66/whisper-large-v3-russian | antony66 | 17.0 | medium | |
| 77 | parakeet-tdt-0.6b-EN-Medical | nvidia/parakeet-tdt-0.6b-v3 | yuriyvnv | 17.0 | medium | |
| 78 | moonshine-tiny-zh | UsefulSensors/moonshine-tiny-zh | UsefulSensors | 17.0 | medium | |
| 79 | rubaistt_v2_medium | — | islomov | 17.0 | medium | |
| 80 | stt_ar_fastconformer_hybrid_large_pcd_v1.0 | nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0 | nvidia | 17.0 | medium | |
| 81 | whisper-tiny-es-mix-norm | openai/whisper-tiny | deepdml | 17.0 | medium | |
| 82 | moonshine-tiny-ko | UsefulSensors/moonshine-tiny-ko | UsefulSensors | 17.0 | medium | |
| 83 | moonshine-tiny-vi | UsefulSensors/moonshine-tiny-vi | UsefulSensors | 17.0 | medium | |
| 84 | whisper-large-v2-fa | openai/whisper-large-v2 | aictsharif | 17.0 | medium | |
| 85 | whisper-tiny-lv | — | RaivisDejus | 17.0 | medium | |
| 86 | moonshine-tiny-zh-gguf | UsefulSensors/moonshine-tiny-zh | handy-computer | 17.0 | medium | |
| 87 | whisper-large-v3-urdu | openai/whisper-large-v3 | kingabzpro | 17.0 | medium | |
| 88 | whisper-large-v3-turbo-turkish | openai/whisper-large-v3-turbo | selimc | 17.0 | medium | |
| 89 | cohere-transcribe-03-2026-ungated | CohereLabs/cohere-transcribe-03-2026 | evewashere | 17.0 | medium | |
| 90 | moonshine-tiny-ar-gguf | UsefulSensors/moonshine-tiny-ar | handy-computer | 17.0 | medium | |
| 91 | moonshine-tiny-ja | UsefulSensors/moonshine-tiny-ja | UsefulSensors | 17.0 | medium | |
| 92 | stt_ar_fastconformer_hybrid_large_pc_v1.0 | nvidia/stt_ar_fastconformer_hybrid_large_pc_v1.0 | nvidia | 17.0 | medium | |
| 93 | whisper-large-v3-cantonese | openai/whisper-large-v3 | khleeloo | 17.0 | medium | |
| 94 | moonshine-tiny-uk-gguf | UsefulSensors/moonshine-tiny-uk | handy-computer | 17.0 | medium | |
| 95 | moonshine-tiny-ar-ONNX | UsefulSensors/moonshine-tiny-ar | onnx-community | 17.0 | medium | |
| 96 | whisper-large-v3-LoS-punctuated | openai/whisper-large-v3 | BSC-LT | 17.0 | medium | |
| 97 | moonshine-tiny-ko-ONNX | UsefulSensors/moonshine-tiny-ko | onnx-community | 17.0 | medium | |
| 98 | whisper-large-v3-turbo-lt | openai/whisper-large-v3-turbo | svogunas | 17.0 | medium | |
| 99 | moonshine-tiny-ja-gguf | UsefulSensors/moonshine-tiny-ja | handy-computer | 17.0 | medium | |
| 100 | moonshine-tiny-uk-ONNX | UsefulSensors/moonshine-tiny-uk | onnx-community | 17.0 | medium | |
| 101 | moonshine-tiny-ko-gguf | UsefulSensors/moonshine-tiny-ko | handy-computer | 17.0 | medium | |
| 102 | whisper-base-es-mix-norm | openai/whisper-base | deepdml | 17.0 | medium | |
| 103 | moonshine-tiny-vi-gguf | UsefulSensors/moonshine-tiny-vi | handy-computer | 17.0 | medium | |
| 104 | moonshine-tiny-ar | UsefulSensors/moonshine-tiny-ar | UsefulSensors | 17.0 | medium | |
| 105 | moonshine-tiny-vi-ONNX | UsefulSensors/moonshine-tiny-vi | onnx-community | 17.0 | medium | |
| 106 | whisper-large-v3-LoS | openai/whisper-large-v3 | BSC-LT | 17.0 | medium | |
| 107 | whisper-large-v3-ca-punctuated-3370h | openai/whisper-large-v3 | BSC-LT | 17.0 | medium | |
| 108 | code-switched-egyptian-arabic-whisper-small | openai/whisper-small | IbrahimAmin | 17.0 | medium | |
| 109 | whisper-large-v3-persian | openai/whisper-large-v3 | nezamisafa | 17.0 | medium | |
| 110 | hviske-v5 | — | syvai | 17.0 | medium | |
| 111 | moonshine-tiny-uk | UsefulSensors/moonshine-tiny-uk | UsefulSensors | 17.0 | medium | |
| 112 | roest-v1-wav2vec2-315m | facebook/wav2vec2-xls-r-300m | CoRal-project | 17.0 | medium | |
| 113 | Nos_ASR-wav2vec2-xls-r-300m-gl | facebook/wav2vec2-xls-r-300m | proxectonos | 17.0 | medium | |
| 114 | whisper-large-v3-turbo-urdu | openai/whisper-large-v3-turbo | kingabzpro | 17.0 | medium | |
| 115 | Sophea-Canary-ASR | nvidia/canary-1b-v2 | KIEFERSA | 17.0 | medium | |
| 116 | whisper-large-v3-high-mixed-nl | openai/whisper-large-v3 | yuriyvnv | 17.0 | medium | |
| 117 | whisper-large-v3-turbo-russian | openai/whisper-large-v3-turbo | dvislobokov | 17.0 | medium | |
| 118 | Shrutimala_Bangla_ASR | facebook/w2v-bert-2.0 | sazzadul | 17.0 | medium | |
| 119 | cohere-transcribe-03-2026-gguf | CohereLabs/cohere-transcribe-03-2026 | memoravox | 17.0 | medium | |
| 120 | whisper-large-v3-turbo-es | openai/whisper-large-v3-turbo | adriszmar | 17.0 | medium | |
| 121 | parakeet-tdt-0.6b-portuguese | nvidia/parakeet-tdt-0.6b-v3 | yuriyvnv | 17.0 | medium | |
| 122 | wav2vec2-large-mms-1b-yoruba-test | facebook/mms-1b-all | ogbi | 16.1 | medium | |
| 123 | Audar-ASR-V1-Flash | — | audarai | 16.02 | medium | CommonVoice-18 |
| 124 | wav2vec2-BERT-cantonese | — | alvanlii | 16.0 | medium | |
| 125 | whisper-small-cantonese | openai/whisper-small | alvanlii | 16.0 | medium | |
| 126 | distil-whisper-large-v3-ptbr | distil-whisper/distil-large-v3 | freds0 | 16.0 | medium | |
| 127 | whisper-large-v3-it-cv16 | openai/whisper-large | fsicoli | 16.0 | medium | |
| 128 | wav2vec2-large-mms-1b-hungarian | facebook/mms-1b-all | GaborMadarasz | 16.0 | medium | Common Voice (500 held-out) |
| 129 | stt_pt_fastconformer_hybrid_large_pc | nvidia/stt_pt_fastconformer_hybrid_large_pc | nvidia | 16.0 | medium | |
| 130 | audio-flamingo-3-hf | nvidia/audio-flamingo-3-hf | nvidia | 15.0 | medium | |
| 131 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | handy-computer | 15.0 | medium | |
| 132 | egyptian-arabic-wav2vec2-xlsr-53 | omarxadel/wav2vec2-large-xlsr-53-arabic-egyptian | IbrahimAmin | 15.0 | medium | |
| 133 | Voxtral-Mini-3B-2507-AWQ4-ARG | mistralai/Voxtral-Mini-3B-2507 | juanginer | 15.0 | medium | |
| 134 | Voxtral-Mini-3B-2507-AWQ4-GEN | mistralai/Voxtral-Mini-3B-2507 | juanginer | 15.0 | medium | |
| 135 | audio-flamingo-3 | nvidia/audio-flamingo-3 | nvidia | 15.0 | medium | |
| 136 | Voxtral-Mini-3B-2507-AWQ4-EN | mistralai/Voxtral-Mini-3B-2507 | juanginer | 15.0 | medium | |
| 137 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | memoravox | 15.0 | medium | |
| 138 | audio-flamingo-3-chat | nvidia/audio-flamingo-3 | nvidia | 15.0 | medium | |
| 139 | whisper-medium-et | — | TalTechNLP | 14.7 | medium | Common Voice 11.0 |
| 140 | whisper-large-v3-vaani-hindi | openai/whisper-small | ARTPARK-IISc | 13.84 | medium | Commonvoice |
| 141 | whisper-medium-et | — | TalTechNLP | 13.8 | medium | Common Voice 8.0 |
| 142 | xls-r-300m-et | — | TalTechNLP | 13.4 | medium | Common Voice 8.0 |
| 143 | parakeet-0.6b-ja-coreml | nvidia/parakeet-tdt_ctc-0.6b-ja | FluidInference | 13.3 | medium | Mozilla Common Voice 16.1 test |
| 144 | distil-large-v3 | distil-whisper/distil-large-v3 | distil-whisper | 13.0 | medium | |
| 145 | distil-small.en | distil-whisper/distil-small.en | distil-whisper | 13.0 | medium | |
| 146 | distil-medium.en | — | distil-whisper | 13.0 | medium | |
| 147 | distil-large-v2 | distil-whisper/distil-large-v3 | distil-whisper | 13.0 | medium | |
| 148 | whisper-large-v3-french | — | bofenghuang | 13.0 | medium | |
| 149 | Whisper-Medicalv1 | — | Crystalcareai | 13.0 | medium | |
| 150 | distill-whisper-th-small | — | biodatlab | 13.0 | medium | |
| 151 | whisper-th-medium-timestamp | biodatlab/whisper-th-medium-combined | biodatlab | 13.0 | medium | |
| 152 | distill-whisper-th-medium | — | biodatlab | 13.0 | medium | |
| 153 | whisper-hinglish-preview | ARTPARK-IISc/whisper-large-v3-vaani-hindi | Trelis | 12.86 | medium | Common Voice Hindi (cv-hi) |
| 154 | tara | — | Trelis | 12.51 | medium | [CommonVoice-hi](https://huggingface.co/datasets/Trelis/vistaar-hi-commonvoice-test) |
| 155 | xls-r-300m-et | — | TalTechNLP | 12.5 | medium | Common Voice 6.1 |
| 156 | stt_pl_fastconformer_hybrid_large_pc | nvidia/stt_pl_fastconformer_hybrid_large_pc | nvidia | 12.0 | medium | |
| 157 | stt_it_fastconformer_hybrid_large_pc | nvidia/stt_it_fastconformer_hybrid_large_pc | nvidia | 12.0 | medium | |
| 158 | whisper-large-v3-turbo-cantonese-yue-english | openai/whisper-large-v3-turbo | JackyHoCL | 11.89 | medium | mozilla-foundation/common_voice_16_1 |
| 159 | japanese-hubert-base-k2-rs35kh | reazon-research/japanese-hubert-base-k2 | reazon-research | 11.59 | high | TEDxJP-10K⬇ |
| 160 | asr-wav2vec2-ctc-french | — | bofenghuang | 11.0 | medium | |
| 161 | whisper-podlodka-turbo | openai/whisper-large-v3-turbo | bond005 | 11.0 | medium | |
| 162 | whisper-large-finnish-v3 | — | Finnish-NLP | 11.0 | medium | |
| 163 | whisper-small-sinhala | openai/whisper-small | Lingalingeswaran | 11.0 | medium | |
| 164 | whisper-medium-id | openai/whisper-medium | cahya | 11.0 | medium | |
| 165 | whisper-tiny-ja | openai/whisper-tiny | zubokol | 11.0 | medium | |
| 166 | whisper-medium-ml | openai/whisper-medium | thennal | 11.0 | medium | |
| 167 | tarbiyah-ai-whisper-medium-merged | openai/whisper-medium | Habib-HF | 11.0 | medium | |
| 168 | whisper-enhanced-ml | nurzhanit/whisper-enhanced-ml | nurzhanit | 11.0 | medium | |
| 169 | whisper-large-v2-marathi | — | DrishtiSharma | 11.0 | medium | |
| 170 | swahili-wav2vec2-asr | eddiegulay/wav2vec2-large-xlsr-mvc-swahili | RareElf | 11.0 | medium | |
| 171 | whisper-large-v2-pl-v2 | — | bardsai | 11.0 | medium | |
| 172 | whisper-small-hi | openai/whisper-small | sanchit-gandhi | 11.0 | medium | |
| 173 | japanese-zipformer-base-k2-rs35kh-bpe | reazon-research/japanese-zipformer-base-k2 | reazon-research | 11.0 | high | TEDxJP-10K⬇ |
| 174 | whisper-large-v2-malayalam | — | DrishtiSharma | 11.0 | medium | |
| 175 | Whisper_Largev2-Swahili-Decodis_Comb_FT | openai/whisper-large-v2 | RafatK | 11.0 | medium | |
| 176 | Whisper_Largev2-Swahili-Decodis_Base | openai/whisper-large-v2 | RafatK | 11.0 | medium | |
| 177 | whisper-large-v3-Thai | openai/whisper-large-v3 | liqi03 | 11.0 | medium | |
| 178 | ukrainian-data2vec-asr | — | Respeecher | 11.0 | medium | |
| 179 | wav2vec2-xls-r-300m-cv8-turkish | — | mpoyraz | 10.61 | medium | Common Voice 8 TR test split |
| 180 | parakeet-0.6b-ja-coreml | nvidia/parakeet-tdt_ctc-0.6b-ja | FluidInference | 10.2 | medium | Mozilla Common Voice 16.1 dev |
| 181 | w2v-bert-punjabi | — | kdcyberdude | 10.18 | medium | |
| 182 | stt_ru_conformer_ctc_large | nvidia/stt_ru_conformer_ctc_large | nvidia | 10.0 | medium | |
| 183 | stt_ru_conformer_transducer_large | nvidia/stt_ru_conformer_transducer_large | nvidia | 10.0 | medium | |
| 184 | Breeze-ASR-25 | openai/whisper-large-v2 | MediaTek-Research | 9.84 | medium | CommonVoice16-zh-TW |
| 185 | Breeze-ASR-25-gguf | MediaTek-Research/Breeze-ASR-25 | handy-computer | 9.84 | medium | CommonVoice16-zh-TW |
| 186 | kotoba-whisper-bilingual-v1.0 | — | kotoba-tech | 9.8 | low | |
| 187 | wav2vec2-large-uralic-voxpopuli-v2-finnish | — | Finnish-NLP | 9.0 | medium | |
| 188 | whisper-small-cv11-french | — | bofenghuang | 9.0 | medium | |
| 189 | wav2vec2-xls-r-300m-bengali-commonvoice | — | shahruk10 | 9.0 | medium | |
| 190 | whisper-medium-portuguese | — | pierreguillou | 9.0 | medium | |
| 191 | whisper-small-cv11-german | — | bofenghuang | 9.0 | medium | |
| 192 | parakeet-tdt_ctc-1.1b-gguf | nvidia/parakeet-tdt_ctc-1.1b | handy-computer | 8.69 | low | |
| 193 | parakeet-tdt_ctc-1.1b | nvidia/parakeet-tdt_ctc-1.1b | nvidia | 8.69 | low | |
| 194 | wav2vec2-xls-r-300m-cv7-turkish | — | mpoyraz | 8.62 | medium | Common Voice 7 TR test split |
| 195 | parakeet-tdt-0.6b-EN-Medical | nvidia/parakeet-tdt-0.6b-v3 | yuriyvnv | 8.58 | medium | 🗣️ Common Voice 17 EN (test) |
| 196 | CrisperWhisper | openai/whisper-large-v3 | nyralabs | 8.19 | medium | [CommonVoice](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0) |
| 197 | CrisperWhisper | openai/whisper-large-v3 | unsloth | 8.19 | medium | [CommonVoice](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0) |
| 198 | wav2vec2-xls-r-300m-cs-250 | facebook/wav2vec2-xls-r-300m | comodoro | 8.0 | medium | |
| 199 | romanian-wav2vec2 | facebook/wav2vec2-xls-r-300m | gigant | 8.0 | medium | |
| 200 | wav2vec2-large-xls-r-300m-Urdu | facebook/wav2vec2-xls-r-300m | kingabzpro | 8.0 | medium | |
| 201 | wav2vec2-xls-r-300m-ftspeech | facebook/wav2vec2-xls-r-300m | saattrupdan | 8.0 | medium | |
| 202 | wav2vec2-xls-r-300m-sk-cv8 | — | comodoro | 8.0 | medium | |
| 203 | wav2vec2-xls-r-1b-portuguese | — | jonatasgrosman | 8.0 | medium | |
| 204 | kotoba-whisper-v2.0 | kotoba-tech/kotoba-whisper-v2.0 | kotoba-tech | 8.0 | medium | |
| 205 | wav2vec2-xls-r-1b-russian | — | jonatasgrosman | 8.0 | medium | |
| 206 | kotoba-whisper-v2.1 | — | kotoba-tech | 8.0 | medium | |
| 207 | wav2vec2-xls-r-1b-english | — | jonatasgrosman | 8.0 | medium | |
| 208 | kotoba-whisper-v1.1 | — | kotoba-tech | 8.0 | medium | |
| 209 | wav2vec2-xls-r-1b-spanish | — | jonatasgrosman | 8.0 | medium | |
| 210 | wav2vec2-xls-r-1b-german | — | jonatasgrosman | 8.0 | medium | |
| 211 | wav2vec2-xls-r-300m-cv8-turkish | — | mpoyraz | 8.0 | medium | |
| 212 | kotoba-whisper-v1.0 | — | kotoba-tech | 8.0 | medium | |
| 213 | wav2vec2-base-vietnamese-160h | facebook/wav2vec2-base | khanhld | 8.0 | medium | |
| 214 | parakeet-0.6b-ja-coreml | nvidia/parakeet-tdt_ctc-0.6b-ja | FluidInference | 8.0 | medium | |
| 215 | wav2vec2-xls-r-1b-french | — | jonatasgrosman | 8.0 | medium | |
| 216 | wav2vec2-xls-r-1b-polish | — | jonatasgrosman | 8.0 | medium | |
| 217 | Qwen3-ASR-1.7B-JA-Anime-Galgame | Qwen/Qwen3-ASR-1.7B | jaykwok | 8.0 | medium | |
| 218 | whisper-medium-et | — | TalTechNLP | 8.0 | medium | |
| 219 | Nos_ASR-wav2vec2-xls-r-300m-gl | facebook/wav2vec2-xls-r-300m | proxectonos | 7.85 | medium | Common Voice 17.0 |
| 220 | parakeet-0.6b-ja-coreml | nvidia/parakeet-tdt_ctc-0.6b-ja | FluidInference | 7.2 | medium | Mozilla Common Voice 8.0 test |
| 221 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | handy-computer | 7.17 | medium | CommonVoice 15 FR |
| 222 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | memoravox | 7.17 | medium | CommonVoice 15 FR |
| 223 | wav2vec2-large-xlsr-53-th | — | airesearch | 7.0 | medium | |
| 224 | wav2vec2-xls-r-300m-cv7-turkish | — | mpoyraz | 7.0 | medium | |
| 225 | parakeet-ctc-0.6b-gguf | nvidia/parakeet-ctc-0.6b | handy-computer | 7.0 | low | |
| 226 | parakeet-ctc-0.6b | nvidia/parakeet-ctc-0.6b | nvidia | 7.0 | low | |
| 227 | wav2vec2-xlsr-300m-finnish-lm | — | Finnish-NLP | 7.0 | medium | |
| 228 | bp500-base100k_voxpopuli | — | lgris | 7.0 | medium | |
| 229 | parakeet-ctc-0.6b-GGUF | nvidia/parakeet-ctc-0.6b | cstr | 7.0 | medium | |
| 230 | wav2vec2-xlsr-1b-finnish-lm-v2 | — | Finnish-NLP | 7.0 | medium | |
| 231 | Kabyle_xlsr | — | Akashpb13 | 7.0 | medium | |
| 232 | stt_fr_conformer_ctc_large | nvidia/stt_fr_conformer_ctc_large | nvidia | 7.0 | medium | |
| 233 | Qwen3-ASR-1.7B-NL | Qwen/Qwen3-ASR-1.7B | yuriyvnv | 6.7 | medium | Common Voice 17 (test) |
| 234 | tara | — | Trelis | 6.68 | medium | [CommonVoice-en](https://huggingface.co/datasets/Trelis/cv-en-scripted-test-500) |
| 235 | Qwen3-ASR-1.7B-NL | Qwen/Qwen3-ASR-1.7B | yuriyvnv | 6.68 | medium | Common Voice 22 (test) |
| 236 | chunkformer-ctc-large-vie | — | khanhld | 6.66 | low | |
| 237 | parakeet-ctc-1.1b | nvidia/parakeet-ctc-1.1b | nvidia | 6.53 | low | |
| 238 | parakeet-ctc-1.1b-gguf | nvidia/parakeet-ctc-1.1b | handy-computer | 6.53 | low | |
| 239 | parakeet-ctc-1.1b-GGUF | nvidia/parakeet-ctc-1.1b | cstr | 6.53 | medium | |
| 240 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | handy-computer | 6.5 | medium | CommonVoice 15 EN |
| 241 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | memoravox | 6.5 | medium | CommonVoice 15 EN |
| 242 | wav2vec2-large-xlsr-53-portuguese | facebook/wav2vec2-large-xlsr-53-portuguese | jonatasgrosman | 6.1 | medium | |
| 243 | wav2vec2-large-xlsr-53-russian | — | jonatasgrosman | 6.1 | medium | |
| 244 | wav2vec2-large-xlsr-53-polish | facebook/wav2vec2-large-xlsr-53-polish | jonatasgrosman | 6.1 | medium | |
| 245 | wav2vec2-large-xlsr-53-dutch | facebook/wav2vec2-large-xlsr-53-dutch | jonatasgrosman | 6.1 | medium | |
| 246 | wav2vec2-large-xlsr-53-japanese | jonatasgrosman/wav2vec2-large-xlsr-53-japanese | jonatasgrosman | 6.1 | medium | |
| 247 | wav2vec2-large-xlsr-53-greek | — | jonatasgrosman | 6.1 | medium | |
| 248 | wav2vec2-large-xlsr-53-arabic | jonatasgrosman/wav2vec2-large-xlsr-53-arabic | jonatasgrosman | 6.1 | medium | |
| 249 | wav2vec2-large-xlsr-53-hungarian | — | jonatasgrosman | 6.1 | medium | |
| 250 | wav2vec2-large-xlsr-53-chinese-zh-cn | jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn | jonatasgrosman | 6.1 | medium | |
| 251 | wav2vec2-large-xlsr-53-persian | — | jonatasgrosman | 6.1 | medium | |
| 252 | wav2vec2-large-xlsr-53-finnish | — | jonatasgrosman | 6.1 | medium | |
| 253 | wav2vec2-large-xlsr-catala | — | softcatala | 6.1 | medium | |
| 254 | wav2vec2-large-xlsr-53-english | jonatasgrosman/wav2vec2-large-xlsr-53-english | jonatasgrosman | 6.1 | medium | |
| 255 | wav2vec2-large-xlsr-53-spanish | facebook/wav2vec2-large-xlsr-53-spanish | jonatasgrosman | 6.1 | medium | |
| 256 | wav2vec2-large-xlsr-53-french | facebook/wav2vec2-large-xlsr-53-french | jonatasgrosman | 6.1 | medium | |
| 257 | wav2vec2-large-xlsr-53-german | facebook/wav2vec2-large-xlsr-53-german | jonatasgrosman | 6.1 | medium | |
| 258 | wav2vec2-large-xlsr-53-italian | facebook/wav2vec2-large-xlsr-53-italian | jonatasgrosman | 6.1 | medium | |
| 259 | xls-r-300m-et | — | TalTechNLP | 6.1 | medium | |
| 260 | wav2vec2-large-xlsr-open-brazilian-portuguese | — | lgris | 6.1 | medium | |
| 261 | wav2vec2-large-chinese-zh-cn | — | wbbbbb | 6.1 | medium | |
| 262 | wav2vec2-large-xlsr-open-brazilian-portuguese-v2 | — | lgris | 6.1 | medium | |
| 263 | wav2vec2-large-100k-voxpopuli-catala | — | ccoreilly | 6.1 | medium | |
| 264 | parakeet-rnnt-0.6b | nvidia/parakeet-rnnt-0.6b | nvidia | 6.05 | low | |
| 265 | parakeet-rnnt-0.6b-gguf | nvidia/parakeet-rnnt-0.6b | handy-computer | 6.05 | low | |
| 266 | parakeet-rnnt-0.6b-gguf | nvidia/parakeet-rnnt-0.6b | memoravox | 6.05 | low | |
| 267 | wav2vec2-large-ru-golos-with-lm | — | bond005 | 6.0 | medium | |
| 268 | whisper-large-v3-high-mixed-nl | openai/whisper-large-v3 | yuriyvnv | 5.49 | medium | Common Voice Only |
| 269 | parakeet-tdt-1.1b-gguf | nvidia/parakeet-tdt-1.1b | handy-computer | 5.48 | low | |
| 270 | parakeet-tdt-1.1b | nvidia/parakeet-tdt-1.1b | nvidia | 5.48 | low | |
| 271 | parakeet-rnnt-1.1b-gguf | nvidia/parakeet-rnnt-1.1b | handy-computer | 5.39 | low | |
| 272 | parakeet-rnnt-1.1b | nvidia/parakeet-rnnt-1.1b | nvidia | 5.39 | low | |
| 273 | whisper-large-v3-turbo-russian-codeswitch | coriollon/whisper-large-v3-turbo-russian | coriollon | 5.33 | medium | Common Voice 21 RU |
| 274 | T-one | — | t-tech | 5.32 | medium | CommonVoice 19 (test split) |
| 275 | whisper-podlodka-turbo | openai/whisper-large-v3-turbo | bond005 | 5.22 | medium | common_voice_11_0 |
| 276 | parakeet-tdt-0.6b-v3-ptBR-TAGARELA-onnx-int8 | alefiury/parakeet-tdt-0.6b-v3-ptBR-TAGARELA-onnx | calneymgp | 5.1 | low | |
| 277 | whisper-large-v3-lv-late-cv19 | openai/whisper-large-v3 | AiLab-IMCS-UL | 4.8 | medium | Latvian Common Voice 19.0 test set (VW) - formatted |
| 278 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | handy-computer | 4.73 | medium | CommonVoice 15 DE |
| 279 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | memoravox | 4.73 | medium | CommonVoice 15 DE |
| 280 | audio-codec-44khz | nvidia/audio-codec-44khz | nvidia | 4.53 | medium | CommonVoice |
| 281 | audio-codec-22khz | nvidia/audio-codec-22khz | nvidia | 4.53 | medium | CommonVoice |
| 282 | LFM2.5-Audio-1.5B-JP | LiquidAI/LFM2.5-Audio-1.5B | LiquidAI | 4.42 | high | |
| 283 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | handy-computer | 4.02 | medium | CommonVoice 15 ES |
| 284 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | memoravox | 4.02 | medium | CommonVoice 15 ES |
| 285 | wav2vec2-large-uralic-voxpopuli-v2-finnish | — | Finnish-NLP | 3.9 | medium | [Common Voice 9.0 Finnish train + evaluation + other splits](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0) |
| 286 | whisper-large-v3-turbo-german | primeline/whisper-large-v3-german | primeline | 3.85 | medium | common_voice_19_0 |
| 287 | whisper-large-v3-turbo-german-ct2 | primeline/whisper-large-v3-german | jimmymeister | 3.85 | medium | common_voice_19_0 |
| 288 | TEA-ASR-1 | Qwen/Qwen3-ASR-1.7B | JacobLinCool | 3.64 | medium | CommonVoice 19 (zh-TW) |
| 289 | TEA-ASR-1.1 | Qwen/Qwen3-ASR-1.7B | JacobLinCool | 3.58 | medium | CommonVoice 19 (zh-TW) |
| 290 | TEA-ASR-1.1-mini | Qwen/Qwen3-ASR-0.6B | JacobLinCool | 3.58 | medium | CommonVoice 19 (zh-TW) |
| 291 | Test | — | AbelWa | 3.55 | low | |
| 292 | wav2vec2-xlsr-300m-finnish-lm | — | Finnish-NLP | 3.52 | medium | [Common Voice 7.0 Finnish train + evaluation + other splits](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) |
| 293 | wav2vec2-xlsr-1b-finnish-lm-v2 | — | Finnish-NLP | 3.52 | medium | [Common Voice 7.0 Finnish train + evaluation + other splits](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) |
| 294 | whisper-large-v3-lv-late-cv19 | openai/whisper-large-v3 | AiLab-IMCS-UL | 3.2 | medium | Latvian Common Voice 19.0 test set (VW) - normalized |
| 295 | wav2vec2-large-xlsr-53-greek | — | lighteternal | 2.88 | medium | CER on CommonVoice Test (%) * |
| 296 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | handy-computer | 2.57 | medium | CommonVoice 15 PT |
| 297 | granite-speech-4.1-2b-nar-gguf | ibm-granite/granite-speech-4.1-2b-nar | memoravox | 2.57 | medium | CommonVoice 15 PT |