| 1 | mms-300m-waxal-lug | facebook/mms-300m | waxal-benchmarking | 100.0 | low | |
| 2 | mms-300m-waxal-sna | facebook/mms-300m | waxal-benchmarking | 100.0 | low | |
| 3 | mms-300m-waxal-lin | facebook/mms-300m | waxal-benchmarking | 100.0 | low | |
| 4 | mms-300m-waxal-ach | facebook/mms-300m | waxal-benchmarking | 100.0 | low | |
| 5 | mms-300m-waxal-nyn | facebook/mms-300m | waxal-benchmarking | 100.0 | low | |
| 6 | mms-300m-waxal-mas | facebook/mms-300m | waxal-benchmarking | 100.0 | low | |
| 7 | Phi-4-multimodal-instruct | microsoft/Phi-4-multimodal-instruct | microsoft | 99.16 | low | fleurs-ko2en-cot | fleurs-en2ko-cot |
| 8 | Phi-4-multimodal-instruct | microsoft/Phi-4-multimodal-instruct | Lexius | 99.16 | low | fleurs-ko2en-cot | fleurs-en2ko-cot |
| 9 | whisper-small-lingala-qlora | openai/whisper-small | Elod1e | 97.93 | medium | |
| 10 | wav2vec2-large-uralic-voxpopuli-v2-finnish | — | Finnish-NLP | 90.0 | high | |
| 11 | whisper-large-v2-translate-zh-v0.2-st-ct2 | openai/whisper-large-v2 | chickenrice0721 | 66.02 | medium | |
| 12 | wav2vec2-ljspeech-gruut | — | bookbot | 58.0 | low | |
| 13 | phoneme-scorer-v2-wav2vec2 | — | ct-vikramanantha | 58.0 | low | |
| 14 | MioTTS-0.1B | tiiuae/Falcon-H1-Tiny-Multilingual-100M-Base | Aratako | 56.96 | low | |
| 15 | moonshine-base-bn | UsefulSensors/moonshine-base | Sanjidh090 | 45.54 | low | |
| 16 | qwen3-asr-0.6b-arabic-dialectal | Qwen/Qwen3-ASR-0.6B-hf | oddadmix | 45.4 | low | |
| 17 | PrimeTTS | owensong/Inflect-Nano-v1 | Luigi | 45.0 | medium | |
| 18 | inflect-v2-coreml | owensong/Inflect-Micro-v2 | FluidInference | 44.0 | low | |
| 19 | qwen3-asr-0.6b-arabic-dialectal | Qwen/Qwen3-ASR-0.6B-hf | oddadmix | 40.8 | high | Zero-shot WER |
| 20 | monsoon-whisper-medium-gigaspeech2 | — | typhoon-ai | 37.55 | high | |
| 21 | MSP-Visual | — | MahmoodAnaam | 37.25 | medium | |
| 22 | whisper-tiny-waxal-lin | openai/whisper-tiny | waxal-benchmarking | 30.9 | medium | **Test CER** |
| 23 | whisper-tiny-waxal-lin | openai/whisper-tiny | waxal-benchmarking | 30.9 | medium | **CER** |
| 24 | Breeze-ASR-26 | openai/whisper-large-v2 | MediaTek-Research | 30.7 | low | |
| 25 | cohere-transcribe-arabic-07-2026-dialectal-v2 | CohereLabs/cohere-transcribe-arabic-07-2026 | oddadmix | 29.4 | medium | |
| 26 | whisper-tiny-grpo-5e2f49e-cv22-tiny-sftadaptive | openai/whisper-tiny | wrice | 29.0 | medium | |
| 27 | whisper-large-v3-turbo-arabic-dialectal | openai/whisper-large-v3-turbo | oddadmix | 27.8 | low | |
| 28 | whisper-tiny-grpo-4bddbd7-cv22-tiny-klbeta02 | openai/whisper-tiny | wrice | 27.0 | medium | |
| 29 | cdli-whisper-ml-lug-swa-sunbird-full-a40 | Sunbird/asr-whisper-large-v3-salt | KasuleTrevor | 26.33 | medium | |
| 30 | whisper-tiny-mla-24lang | openai/whisper-tiny | burakaydinofficial | 25.1 | high | |
| 31 | whisper-small-burmese-v2 | myatsu/whisper-small-burmese | myatsu | 24.96 | medium | |
| 32 | whisper-tiny-waxal-lin | openai/whisper-tiny | waxal-benchmarking | 23.46 | low | |
| 33 | whisper-small-japanese | — | Ivydata | 23.1 | high | |
| 34 | wav2vec2-xlsr-multilingual-56 | — | voidful | 22.82 | high | |
| 35 | whisper_small_ps_augmented | ihanif/whisper_small_ps_augmented | ihanif | 22.68 | medium | |
| 36 | wav2vec2-large-xlsr-53-punjabi | Harveenchadha/vakyansh-wav2vec2-punjabi-pam-10 | kingabzpro | 22.38 | medium | |
| 37 | whisper-small-waxal-lin | openai/whisper-small | waxal-benchmarking | 21.7 | medium | **Test CER** |
| 38 | whisper-small-waxal-lin | openai/whisper-small | waxal-benchmarking | 21.7 | medium | **CER** |
| 39 | cdli-whisper-ml-lug-swa-sunbird-full-a40-lr1e4 | Sunbird/asr-whisper-large-v3-salt | KasuleTrevor | 21.49 | medium | |
| 40 | qwen3-asr-0.6b-arabic-dialectal-v2 | Qwen/Qwen3-ASR-0.6B-hf | oddadmix | 21.48 | low | |
| 41 | cdli-whisper-ml-ugeng-lug-swa-sunbird-full-a40-lr1e4-5k | Sunbird/asr-whisper-large-v3-salt | KasuleTrevor | 21.44 | medium | |
| 42 | whisper-tiny-khmer | openai/whisper-tiny | sengtha | 21.32 | medium | |
| 43 | moulsot.v0.3 | Qwen/Qwen3-ASR-1.7B | atlasia | 21.3 | medium | |
| 44 | cdli-whisper-ml-ugeng-lug-swa-sunbird-full-a40-lr5e5 | Sunbird/asr-whisper-large-v3-salt | KasuleTrevor | 20.41 | medium | |
| 45 | wav2vec2-large-xlsr-53-japanese | jonatasgrosman/wav2vec2-large-xlsr-53-japanese | jonatasgrosman | 20.16 | high | |
| 46 | cdli-whisper-ml-lug-swa-sunbird-full-a40-lr5e5-5k | Sunbird/asr-whisper-large-v3-salt | KasuleTrevor | 20.1 | medium | |
| 47 | wav2vec2-xls-r-300m-pashto | facebook/wav2vec2-xls-r-300m | ihanif | 19.72 | medium | |
| 48 | griot-nano-1 | — | Qlerqly | 19.27 | low | |
| 49 | griot-nano-1-onnx | — | Qlerqly | 19.27 | low | |
| 50 | wav2vec2-large-xlsr-53-chinese-zh-cn | jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn | jonatasgrosman | 19.03 | high | |
| 51 | Sunflower-Gemma4-E2B | google/gemma-4-E2B-it | Sunbird | 18.9 | low | |
| 52 | mms-300m-waxal-lin | facebook/mms-300m | waxal-benchmarking | 18.9 | medium | **Test CER** |
| 53 | mms-300m-waxal-lin | facebook/mms-300m | waxal-benchmarking | 18.9 | medium | **CER** |
| 54 | whisper-base-mla-24lang | openai/whisper-base | burakaydinofficial | 18.7 | high | |
| 55 | wav2vec2-large-xlsr-53-cantonese | — | CAiRE | 18.55 | medium | |
| 56 | wav2vec2-large-xlsr-53-arabic | jonatasgrosman/wav2vec2-large-xlsr-53-arabic | jonatasgrosman | 18.18 | high | |
| 57 | wav2vec2-large-japanese | — | NTQAI | 18.15 | high | |
| 58 | wav2vec2-large-xlsr-japanese | — | vumichien | 17.85 | medium | |
| 59 | cohere-transcribe-arabic-07-2026-dialectal | CohereLabs/cohere-transcribe-arabic-07-2026 | oddadmix | 17.4 | low | |
| 60 | whisper-large-v2-vietnamese-lyrics-transcription | openai/whisper-large-v2 | kelvinbksoh | 17.14 | high | |
| 61 | mms-300m-waxal-ach | facebook/mms-300m | waxal-benchmarking | 17.1 | medium | **Test CER** |
| 62 | mms-300m-waxal-ach | facebook/mms-300m | waxal-benchmarking | 17.1 | medium | **CER** |
| 63 | whisper-small-waxal-lin | openai/whisper-small | waxal-benchmarking | 16.91 | low | |
| 64 | whisper-small-egyptian-arabic | — | MAdel121 | 16.76 | medium | |
| 65 | Qwen3-ASR-1.7B-JA-Anime-Galgame | Qwen/Qwen3-ASR-1.7B | jaykwok | 16.73 | low | |
| 66 | whisper-small-egyptian-arabic | — | MAdel121 | 16.7 | medium | CER |
| 67 | nemotron-ocr-v1 | nvidia/nemotron-ocr-v1 | nvidia | 16.33 | medium | Character Error Rate |
| 68 | wav2vec2-large-xlsr-53-th | — | airesearch | 16.23 | low | |
| 69 | wav2vec2-xls-r-1b-japanese-hiragana-katakana | — | AndrewMcDowell | 16.09 | medium | |
| 70 | BlueMagpie-TTS | OpenFormosa/BlueMagpie-TTS | OpenFormosa | 15.37 | low | |
| 71 | whisper-small-arabic-dialectal-v2 | openai/whisper-small | oddadmix | 15.28 | low | |
| 72 | uk_wav2vec2_with_stress_mark | mouseyy/result_data_2-3 | mouseyy | 15.12 | medium | |
| 73 | whisper-small-arabic-dialectal | openai/whisper-small | oddadmix | 15.1 | low | |
| 74 | whisper-small-arabic-dialectal | openai/whisper-small | oddadmix | 15.1 | high | Zero-shot WER |
| 75 | batisay-ko-turbo | openai/whisper-large-v3-turbo | batiai | 14.85 | low | |
| 76 | MSP-Audio | facebook/wav2vec2-large-robust-ft-libri-960h | MahmoodAnaam | 14.74 | medium | |
| 77 | azerbaijani-whisper-turbo | openai/whisper-large-v3-turbo | LocalDoc | 14.52 | low | |
| 78 | azerbaijani-whisper-small | openai/whisper-small | LocalDoc | 14.52 | high | |
| 79 | parakeet-tdt-0.6b-EN-Medical | nvidia/parakeet-tdt-0.6b-v3 | yuriyvnv | 14.16 | low | Zero-shot WER | Zero-shot CER |
| 80 | whisper-large-v3-turbo-cantonese-yue-english | openai/whisper-large-v3-turbo | JackyHoCL | 13.7 | medium | |
| 81 | wav2vec2-xls-r-300m-sk-cv8 | — | comodoro | 13.33 | medium | |
| 82 | wav2vec2-xls-r-300m-phoneme | — | vitouphy | 13.32 | medium | |
| 83 | wav2vec2-xls-r-latin | facebook/wav2vec2-xls-r-300m | njand | 13.06 | low | |
| 84 | Medical-Whisper-Large-v3 | openai/whisper-large-v3 | Na0s | 13.0 | low | |
| 85 | whisper-finetune-teochew | — | panlr | 12.87 | low | |
| 86 | whisper-small-waxal-ful | openai/whisper-small | waxal-benchmarking | 12.83 | low | |
| 87 | whisper-tiny-waxal-lug | openai/whisper-tiny | waxal-benchmarking | 12.8 | medium | **Test CER** |
| 88 | whisper-tiny-waxal-lug | openai/whisper-tiny | waxal-benchmarking | 12.8 | medium | **CER** |
| 89 | whisper-small-combined-lin-sna-lug-olusola | openai/whisper-small | samolusola-personal | 12.57 | medium | |
| 90 | whisper-large-v3-turbo-arabic-dialectal-v2 | openai/whisper-large-v3-turbo | oddadmix | 12.5 | low | |
| 91 | wav2vec2-large-chinese-zh-cn | — | wbbbbb | 12.3 | high | |
| 92 | whisper-medium-combined-lin-sna-lug-olusola | openai/whisper-medium | samolusola-personal | 12.21 | medium | |
| 93 | whisper-large-v3-arabic-dialectal-v2 | openai/whisper-large-v3 | oddadmix | 12.03 | low | |
| 94 | whisper-small-waxal-ful | openai/whisper-small | waxal-benchmarking | 12.0 | medium | **Test CER** |
| 95 | whisper-small-waxal-ful | openai/whisper-small | waxal-benchmarking | 12.0 | medium | **CER** |
| 96 | whisper-small-mla-24lang | openai/whisper-small | burakaydinofficial | 12.0 | high | |
| 97 | whisper-small-waxal-sna | openai/whisper-small | waxal-benchmarking | 11.96 | low | |
| 98 | whisper-small-hu | openai/whisper-small | SubZtep | 11.7 | low | |
| 99 | MSP-Fusion | — | MahmoodAnaam | 11.67 | medium | |
| 100 | roest-v3-whisper-1.5b | openai/whisper-large-v3 | CoRal-project | 11.6 | low | |
| 101 | roest-v3-wav2vec2-315m | facebook/wav2vec2-xls-r-300m | CoRal-project | 11.6 | low | |
| 102 | FireRedASR2-LLM | — | FireRedTeam | 11.55 | medium | **Avg CER (Dialects, 19 sets)** |
| 103 | whisper-large-v3-turbo-arabic-dialectal | openai/whisper-large-v3-turbo | oddadmix | 11.5 | low | Zero-shot WER |
| 104 | cohere-transcribe-arabic-07-2026-dialectal | CohereLabs/cohere-transcribe-arabic-07-2026 | oddadmix | 11.5 | low | Zero-shot WER |
| 105 | nemotron-asr-litert-zhtw | Luigi/nemotron-3.5-asr-streaming-0.6b-zhtw | Luigi | 11.33 | low | |
| 106 | MOSS-Transcribe-Diarize-MLX-8bit | OpenMOSS-Team/MOSS-Transcribe-Diarize | majentik | 11.1 | low | |
| 107 | whosper-large-v2 | openai/whisper-large-v2 | CAYTU | 11.01 | medium | CER |
| 108 | mms-300m-waxal-mas | facebook/mms-300m | waxal-benchmarking | 11.0 | medium | **Test CER** |
| 109 | mms-300m-waxal-mas | facebook/mms-300m | waxal-benchmarking | 11.0 | medium | **CER** |
| 110 | wav2vec2-large-xlsr-japanese-hiragana | — | vumichien | 10.99 | medium | |
| 111 | nemotron-3.5-swahili-streaming-asr | nvidia/nemotron-3.5-asr-streaming-0.6b | Tonykip | 10.6 | low | |
| 112 | QwenCleo-ASR | Qwen/Qwen3-ASR-1.7B | mohammedaly22 | 10.52 | low | |
| 113 | MSP | — | MahmoodAnaam | 10.5 | medium | |
| 114 | whisper-acft | openai/whisper-tiny | litert-community | 10.4 | medium | |
| 115 | whisper-small-mn | openai/whisper-small | Blgn94 | 10.3 | medium | CER |
| 116 | whisper-tiny-waxal-lug | openai/whisper-tiny | waxal-benchmarking | 10.23 | low | |
| 117 | w2vbert-waxal-multi7 | sulaimank/w2v-bert-waxal | sulaimank | 9.95 | medium | |
| 118 | wav2vec2-large-english-TIMIT-phoneme_v3 | — | speech31 | 9.87 | medium | |
| 119 | typhoon-asr-realtime | nvidia/stt_en_fastconformer_transducer_large | typhoon-ai | 9.84 | medium | |
| 120 | gha-whisper-small-twi-v3 | teckedd/whisper-small-waxal-round2-specaug-v1 | teckedd | 9.58 | medium | |
| 121 | wav2vec2-xls-r-300m-korean | — | w11wo | 9.53 | low | |
| 122 | wav2vec2-arabic-phoneme-asr | facebook/wav2vec2-large-xlsr-53 | MostafaMaroof | 9.5 | medium | **CER** |
| 123 | mms-300m-waxal-nyn | facebook/mms-300m | waxal-benchmarking | 9.5 | medium | **Test CER** |
| 124 | mms-300m-waxal-nyn | facebook/mms-300m | waxal-benchmarking | 9.5 | medium | **CER** |
| 125 | Audar-ASR-V1-Flash | — | audarai | 9.49 | high | |
| 126 | Audar-ASR-V1-Turbo | — | audarai | 9.49 | low | |
| 127 | whisper-large-v3-urdu | openai/whisper-large-v3 | kingabzpro | 9.43 | medium | **CER** |
| 128 | wav2vec2-large-english-phoneme-v2 | — | speech31 | 9.0 | medium | |
| 129 | whisper-medium-full-clinical-r16 | openai/whisper-medium | robello2 | 8.92 | medium | |
| 130 | whisper-large-v3-swahili-afrivoice-cv | openai/whisper-large-v3 | ElizabethMwangi | 8.9 | low | |
| 131 | whisper-large-v3-turbo-urdu | openai/whisper-large-v3-turbo | kingabzpro | 8.79 | medium | **CER** |
| 132 | whisper-tiny_ro-80mel | openai/whisper-tiny | IonGrozea | 8.63 | medium | CER |
| 133 | whisper-small-ja | openai/whisper-small | vumichien | 8.6 | medium | |
| 134 | Chorus-v1 | openai/whisper-large-v3-turbo | Trelis | 8.58 | medium | CER |
| 135 | xlsr-waxal-from-luganda | sulaimank/xls-r-300m-luganda-313hr | sulaimank | 8.53 | medium | |
| 136 | Fun-ASR-Nano-GGUF | — | FunAudioLLM | 8.35 | low | |
| 137 | Fun-ASR-Nano-GGUF | — | nile2000 | 8.35 | low | |
| 138 | whisper-large-v3-turbo-darija | openai/whisper-large-v3-turbo | anaszil | 8.3 | medium | |
| 139 | openai_whisper-large-v3-turbo-NVFP4 | openai/whisper-large-v3-turbo | Reza2kn | 8.3 | low | |
| 140 | whisper-large-v3-turbo-darija | openai/whisper-large-v3-turbo | anaszil | 8.28 | medium | **Character Error Rate (CER)** |
| 141 | wav2vec2-large-xlsr-53-finnish | — | jonatasgrosman | 8.23 | high | |
| 142 | tamil-asr-qwen3 | Qwen/Qwen3-ASR-1.7B | osmapi | 7.95 | low | |
| 143 | asr-wav2vec2-commonvoice-14-en | — | speechbrain | 7.92 | low | |
| 144 | nemo-nano-codec-22khz-0.6kbps-12.5fps | nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps | nvidia | 7.79 | low | |
| 145 | xls-r-uzbek-cv8 | facebook/wav2vec2-xls-r-300m | lucio | 7.77 | medium | |
| 146 | wav2vec2-bloom-speech-tgl | — | sil-ai | 7.69 | medium | |
| 147 | wav2vec2-large-xlsr-53-persian | — | jonatasgrosman | 7.37 | high | |
| 148 | whisper-medium-ml | openai/whisper-medium | thennal | 7.33 | medium | |
| 149 | asr-conformer-transformerlm-ksponspeech | — | speechbrain | 7.33 | low | |
| 150 | wav2vec2-base-korean | facebook/wav2vec2-base | Kkonjeong | 7.3 | medium | |
| 151 | Test | — | AbelWa | 7.3 | low | |
| 152 | whisper-tiny-es-mix-norm | openai/whisper-tiny | deepdml | 7.26 | medium | |
| 153 | whisper-large-v3-urdu | openai/whisper-large-v3 | kingabzpro | 7.2 | medium | |
| 154 | whisper-base-armenian | openai/whisper-base | Chillarmo | 6.98 | medium | **Character Error Rate (CER)** |
| 155 | wav2vec2-xlsr-khmer | — | gagan3012 | 6.95 | medium | |
| 156 | asr-wav2vec2-commonvoice-14-pt | — | speechbrain | 6.85 | low | |
| 157 | my_zh_CN_asr_cv13_model | jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn | tristayqc | 6.74 | medium | |
| 158 | whisper-large-v2-cantonese | openai/whisper-large-v2 | simonl0909 | 6.73 | medium | |
| 159 | whisper-large-v3-turbo-korean | openai/whisper-large-v3-turbo | ghost613 | 6.67 | medium | |
| 160 | whisper-large-v2-mn-13 | — | bayartsogt | 6.6 | medium | |
| 161 | Whisper-Large-v3-turbo-STT-Zeroth-KO-v2 | openai/whisper-large-v3-turbo | o0dimplz0o | 6.6 | medium | |
| 162 | asr-cherokee | facebook/wav2vec2-large-xlsr-53 | charliemcvicker | 6.58 | medium | |
| 163 | qwen3-asr-arabic-ksa | Qwen/Qwen3-ASR-1.7B | vadimbelsky | 6.57 | medium | **CER** |
| 164 | parakeet-0.6b-ja-coreml | nvidia/parakeet-tdt_ctc-0.6b-ja | FluidInference | 6.5 | low | |
| 165 | wav2vec2-base-japanese-asr | facebook/wav2vec2-base | TKU410410103 | 6.46 | medium | |
| 166 | MOSS-Transcribe-Diarize-0.9B-MLX-5bit | OpenMOSS-Team/MOSS-Transcribe-Diarize | aufklarer | 6.36 | low | |
| 167 | swecha-gonthuka-asr | Harveenchadha/wav2vec2-pretrained-clsril-23-10k | swechatelangana | 6.32 | low | |
| 168 | hviske-v5 | — | syvai | 6.3 | low | |
| 169 | wav2vec2-large-xlsr-53-hungarian | — | jonatasgrosman | 6.2 | high | |
| 170 | openai_whisper-large-v3-NVFP4 | openai/whisper-large-v3 | Reza2kn | 6.19 | low | |
| 171 | whisper-base-ar-quran-mix-norm | openai/whisper-base | deepdml | 6.09 | medium | |
| 172 | wav2vec2-base-760-turkish | facebook/wav2vec2-base | ceyda | 6.05 | medium | |
| 173 | wav2vec2-xls-r-300m-hy | — | arampacha | 6.02 | medium | |
| 174 | w2vbert-lingala-waxal | sulaimank/w2v-bert-lingala-109h | sulaimank | 6.0 | medium | |
| 175 | Whisper-Large-v3-xVITA-zhTW | openai/whisper-large-v3 | xCloudinfo | 5.94 | low | |
| 176 | whisper-small-waxal-lug | openai/whisper-small | waxal-benchmarking | 5.93 | low | |
| 177 | whisper-small-pt-cv11-v5 | openai/whisper-small | jonatasgrosman | 5.89 | medium | |
| 178 | w2v-bert-waxal | sulaimank/w2v-bert-lingala-109h | sulaimank | 5.87 | medium | |
| 179 | whisper-base_ro-80mel | openai/whisper-base | IonGrozea | 5.82 | medium | CER |
| 180 | wav2vec2-bert-CV16-en | ylacombe/w2v-bert-2.0 | hf-audio | 5.8 | medium | |
| 181 | wav2vec2-large-xls-r-1b-Swedish | facebook/wav2vec2-xls-r-1b | kingabzpro | 5.75 | medium | |
| 182 | w2v-bert-2.0-khmer-v4 | facebook/w2v-bert-2.0 | Prakmlis | 5.73 | medium | |
| 183 | asr-transformer-aishell | — | speechbrain | 5.6 | low | |
| 184 | whisper-small-waxal-lug | openai/whisper-small | waxal-benchmarking | 5.5 | medium | **Test CER** |
| 185 | whisper-small-waxal-lug | openai/whisper-small | waxal-benchmarking | 5.5 | medium | **CER** |
| 186 | whisper-large-v3-turbo-nepali | openai/whisper-large-v3-turbo | kiranpantha | 5.49 | medium | |
| 187 | whisper-large-v3-turkish-general | openai/whisper-large-v3 | turkmedstt | 5.46 | low | |
| 188 | IndicConformer-GGUF | ai4bharat/indicconformer_stt_hi_hybrid_rnnt_large | Singla0009 | 5.2 | medium | **IndicConformer GGUF (CER)** |
| 189 | wav2vec2-large-mms-1b-hungarian | facebook/mms-1b-all | GaborMadarasz | 5.19 | medium | |
| 190 | surt-small-v3 | openai/whisper-small | surindersinghssj | 5.15 | medium | |
| 191 | za-anv-multilingual-whisper-v3-turbo | openai/whisper-large-v3-turbo | dsfsi-anv | 5.1 | medium | |
| 192 | whisper-small-waxal-sna | openai/whisper-small | waxal-benchmarking | 5.1 | medium | **Test CER** |
| 193 | whisper-small-waxal-sna | openai/whisper-small | waxal-benchmarking | 5.1 | medium | **CER** |
| 194 | kazakh-whisper-large-v3-turbo | openai/whisper-large-v3-turbo | shyngys879 | 4.98 | low | |
| 195 | whisper-small-uyghur-thugy20 | openai/whisper-small | ixxan | 4.93 | medium | |
| 196 | kiswahili_sahihi_asr_adapted_2 | keystats/kiswahili_sahihi_asr | keystats | 4.89 | low | |
| 197 | JaiTTS-F5TTS | SWivid/F5-TTS | JTS-AI | 4.78 | high | |
| 198 | whisper-base-es-mix-norm | openai/whisper-base | deepdml | 4.77 | medium | |
| 199 | wav2vec2-xls-r-300m-bengali | — | arijitx | 4.72 | medium | |
| 200 | nemotron-ocr-v1 | nvidia/nemotron-ocr-v1 | nvidia | 4.53 | medium | Bag-of-character Error Rate |
| 201 | w2vbert-luganda-waxal-punct-v2 | sulaimank/w2vbert-luganda-waxal-stage2 | sulaimank | 4.5 | low | |
| 202 | whisper-large-v3-nepali | openai/whisper-large-v3 | kiranpantha | 4.49 | medium | |
| 203 | xlsr-luganda-waxal | sulaimank/wav2vec2-xlsr-swahili-400hr | sulaimank | 4.46 | medium | |
| 204 | w2vbert-lingala-waxal-punct-v2 | sulaimank/w2vbert-lingala-waxal | sulaimank | 4.37 | low | |
| 205 | mms-300m-waxal-sna | facebook/mms-300m | waxal-benchmarking | 4.3 | medium | **Test CER** |
| 206 | mms-300m-waxal-sna | facebook/mms-300m | waxal-benchmarking | 4.3 | medium | **CER** |
| 207 | Nemotron-3.5-ASR-Streaming-0.6B-CoreML-INT8 | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 4.26 | low | |
| 208 | Nemotron-3.5-ASR-Streaming-0.6B-CoreML-INT8 | nvidia/nemotron-3.5-asr-streaming-0.6b | playstonex | 4.26 | low | |
| 209 | moonshine-tiny-de-fidoriel-GGUF | fidoriel/moonshine-tiny-de | cstr | 4.2 | medium | |
| 210 | nb-wav2vec2-300m-nynorsk | — | NbAiLab | 4.19 | medium | |
| 211 | hviske-v5.3 | syvai/hviske-v5.1 | syvai | 4.17 | low | |
| 212 | f5-tts-quebec-french-finetune | RASPIAUDIO/F5-French-MixedSpeakers-reduced | tontate | 4.1 | medium | CER ↓ |
| 213 | nb-wav2vec2-1b-nynorsk | — | NbAiLab | 4.02 | medium | |
| 214 | whisper-tiny-yoruba-v2 | openai/whisper-tiny | EYEDOL | 3.99 | medium | |
| 215 | kiswahili_sahihi_asr_adapted_2 | keystats/kiswahili_sahihi_asr | keystats | 3.98 | medium | **Final CER** |
| 216 | Nemotron-3.5-ASR-Streaming-0.6B-MLX-5bit | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 3.94 | high | |
| 217 | sauti-asr | microsoft/paza-whisper-large-v3-turbo | msingiai | 3.88 | medium | CER |
| 218 | Nemotron-3.5-ASR-Streaming-0.6B-MLX-8bit | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 3.77 | high | |
| 219 | xlsr-luganda-waxal-pseudo | — | sulaimank | 3.7 | medium | |
| 220 | w2v-xls-r-uk | facebook/wav2vec2-xls-r-300m | Yehor | 3.64 | medium | |
| 221 | sushrota-sanskrit-asr | — | prathoshap | 3.6 | low | |
| 222 | ATC-whisper-turbo-v1 | openai/whisper-large-v3-turbo | SingularityUS | 3.58 | low | |
| 223 | mms-300m-waxal-lug | facebook/mms-300m | waxal-benchmarking | 3.4 | medium | **Test CER** |
| 224 | mms-300m-waxal-lug | facebook/mms-300m | waxal-benchmarking | 3.4 | medium | **CER** |
| 225 | wav2vec2-large-xlsr-53-greek | — | jonatasgrosman | 3.36 | high | |
| 226 | wav2vec2-xls-r-parlaspeech-hr | — | classla | 3.35 | low | |
| 227 | w2v-bert-uk-v2.1 | facebook/w2v-bert-2.0 | Yehor | 3.33 | medium | |
| 228 | wav2vec2-xls-r-300m-cs-250 | facebook/wav2vec2-xls-r-300m | comodoro | 3.29 | medium | |
| 229 | whisper-large-v3-turbo-verbatim-1 | openai/whisper-large-v3-turbo | JacobLinCool | 3.25 | medium | |
| 230 | wav2vec2-large-slavic-parlaspeech-hr | — | classla | 3.11 | low | |
| 231 | firered-asr2-aed-GGUF | FireRedTeam/FireRedASR2-AED | cstr | 3.05 | medium | |
| 232 | FireRedASR2-AED | FireRedTeam/FireRedASR2-AED | FireRedTeam | 3.05 | high | |
| 233 | wav2vec2-large-xls-r-300m-Urdu | facebook/wav2vec2-xls-r-300m | kingabzpro | 3.03 | high | |
| 234 | whisper-small_ro-80mel | openai/whisper-small | IonGrozea | 3.03 | medium | CER |
| 235 | Freya-TTS | — | freyavoice | 3.0 | medium | |
| 236 | hindi-tts-190M | — | 5ivatej | 3.0 | low | |
| 237 | romanian-wav2vec2 | facebook/wav2vec2-xls-r-300m | gigant | 2.94 | medium | |
| 238 | wav2vec2-large-xlsr-53-spanish-with-lm | — | patrickvonplaten | 2.93 | high | |
| 239 | FireRedASR2-LLM | — | FireRedTeam | 2.89 | medium | **Avg CER (Mandarin, 4 sets)** |
| 240 | whisper-large-v3-turbo-armenian | openai/whisper-large-v3-turbo | Chillarmo | 2.86 | low | |
| 241 | whisper-large-v3-turbo-armenian | openai/whisper-large-v3-turbo | Chillarmo | 2.86 | medium | **Character Error Rate (CER)** |
| 242 | w2vbert-luganda-waxal | sulaimank/w2v-bert-2.0-lg-CV-Fleurs-300 | sulaimank | 2.85 | medium | |
| 243 | Whisper-Large-v3-Turbo-CoreML | openai/whisper-large-v3-turbo | aufklarer | 2.72 | low | |
| 244 | whisper-large-finnish-v3 | — | Finnish-NLP | 2.7 | medium | |
| 245 | nb-wav2vec2-300m-bokmaal | — | NbAiLab | 2.69 | medium | |
| 246 | parakeet-tdt-0.6b-portuguese | nvidia/parakeet-tdt-0.6b-v3 | yuriyvnv | 2.69 | low | |
| 247 | wav2vec2-xls-r-300m-cv8-turkish | — | mpoyraz | 2.67 | low | |
| 248 | whisper-medium-hindi-hinglish-asr-fine-tuned | openai/whisper-medium | shujaAK | 2.62 | medium | Character Error Rate (CER) |
| 249 | whisper-medium-hindi-hinglish-asr-fine-tuned | openai/whisper-medium | shujaAK | 2.62 | medium | CER |
| 250 | omnivoice-hakka-community-1 | k2-fsa/OmniVoice | formospeech | 2.61 | low | |
| 251 | omnivoice-hakka-community-1 | k2-fsa/OmniVoice | formospeech | 2.61 | medium | Hakka CER (Avg of sample CERs) |
| 252 | wav2vec2-large-slavic-parlaspeech-hr-lm | — | classla | 2.53 | low | |
| 253 | nb-wav2vec2-1b-bokmaal | — | NbAiLab | 2.48 | medium | |
| 254 | nemo-nano-codec-22khz-1.89kbps-21.5fps | nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps | nvidia | 2.43 | low | |
| 255 | nemo-nano-codec-22khz-1.78kbps-12.5fps | nvidia/nemo-nano-codec-22khz-1.78kbps-12.5fps | nvidia | 2.42 | low | |
| 256 | w2vbert-shona-waxal | sulaimank/W2V2_Bert_Afrivoice_FLEURS_Shona_100hr_v1 | sulaimank | 2.41 | medium | |
| 257 | moonshine-base-de-fidoriel-GGUF | fidoriel/moonshine-base-de | cstr | 2.4 | medium | |
| 258 | moonshine-base-de | UsefulSensors/moonshine-base | fidoriel | 2.4 | medium | |
| 259 | Shrutimala_Bangla_ASR | facebook/w2v-bert-2.0 | sazzadul | 2.39 | medium | |
| 260 | Shenava-Koochik-0.9 | nvidia/stt_en_fastconformer_hybrid_large_streaming_multi | Reza2kn | 2.35 | low | |
| 261 | whisper-medium_ro-80mel | openai/whisper-medium | IonGrozea | 2.31 | medium | CER |
| 262 | Shenava-Koochik-v1.0 | nvidia/stt_fa_fastconformer_hybrid_large | Reza2kn | 2.3 | low | |
| 263 | omnivoice-hakka-community-1 | k2-fsa/OmniVoice | formospeech | 2.29 | medium | Hakka CER (Weighted) |
| 264 | wav2vec2-large-xlsr-53-german-cv9 | — | oliverguhr | 2.27 | medium | |
| 265 | wav2vec2-xls-r-300m-cv7-turkish | — | mpoyraz | 2.26 | low | |
| 266 | best_for_now | openai/whisper-small | MosesJoshuaCoker | 2.18 | medium | Character Error Rate (CER) |
| 267 | low-frame-rate-speech-codec-22khz | nvidia/low-frame-rate-speech-codec-22khz | nvidia | 2.09 | low | |
| 268 | wav2vec2-xlsr-300m-finnish-lm | — | Finnish-NLP | 1.97 | high | |
| 269 | Qwen3-ASR-0.6B-Khmer | Qwen/Qwen3-ASR-0.6B | seanghay | 1.96 | low | |
| 270 | qwen3-asr-0.6b-coreml | Qwen/Qwen3-ASR-0.6B | FluidInference | 1.9 | low | |
| 271 | w2vbert-shona-waxal-punct-v2 | sulaimank/w2vbert-shona-waxal | sulaimank | 1.85 | low | |
| 272 | wav2vec2-large-xlsr-korean | — | kresnik | 1.78 | medium | |
| 273 | fastconformer-quran | nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0 | Muno459 | 1.68 | low | |
| 274 | Nos_ASR-wav2vec2-xls-r-300m-gl | facebook/wav2vec2-xls-r-300m | proxectonos | 1.66 | low | |
| 275 | paligemma2-3b-ft-docci-448 | google/paligemma2-3b-ft-docci-448 | google | 1.6 | low | |
| 276 | paligemma2-3b-pt-448 | google/paligemma2-3b-pt-448 | google | 1.6 | low | |
| 277 | paligemma2-3b-mix-224 | google/paligemma2-3b-mix-224 | google | 1.6 | low | |
| 278 | paligemma2-3b-mix-448 | google/paligemma2-3b-mix-448 | google | 1.6 | low | |
| 279 | paligemma2-3b-pt-224 | google/paligemma2-3b-pt-224 | google | 1.6 | low | |
| 280 | paligemma2-10b-mix-448 | google/paligemma2-10b-mix-448 | google | 1.6 | low | |
| 281 | paligemma2-10b-pt-224 | google/paligemma2-10b-pt-224 | google | 1.6 | low | |
| 282 | paligemma2-3b-pt-896 | google/paligemma2-3b-pt-896 | google | 1.6 | low | |
| 283 | paligemma2-10b-mix-224 | google/paligemma2-10b-mix-224 | google | 1.6 | low | |
| 284 | paligemma2-10b-ft-docci-448 | google/paligemma2-10b-ft-docci-448 | google | 1.6 | low | |
| 285 | paligemma2-28b-pt-896 | google/paligemma2-28b-pt-896 | google | 1.6 | low | |
| 286 | paligemma2-10b-pt-448 | google/paligemma2-10b-pt-448 | google | 1.6 | low | |
| 287 | paligemma2-10b-pt-896 | google/paligemma2-10b-pt-896 | google | 1.6 | low | |
| 288 | whisper-large-v3-lv-late-cv19 | openai/whisper-large-v3 | AiLab-IMCS-UL | 1.6 | low | |
| 289 | paligemma2-28b-pt-448 | google/paligemma2-28b-pt-448 | google | 1.6 | low | |
| 290 | paligemma2-28b-mix-448 | google/paligemma2-28b-mix-448 | google | 1.6 | low | |
| 291 | paligemma2-28b-pt-224 | google/paligemma2-28b-pt-224 | google | 1.6 | low | |
| 292 | paligemma2-3b-pt-448-keras | google/paligemma2-3b-pt-448-keras | google | 1.6 | low | |
| 293 | paligemma2-3b-pt-224-keras | google/paligemma2-3b-pt-224-keras | google | 1.6 | low | |
| 294 | paligemma2-3b-pt-896-keras | google/paligemma2-3b-pt-896-keras | google | 1.6 | low | |
| 295 | paligemma2-10b-pt-448-keras | google/paligemma2-10b-pt-448-keras | google | 1.6 | low | |
| 296 | paligemma2-10b-pt-896-keras | google/paligemma2-10b-pt-896-keras | google | 1.6 | low | |
| 297 | paligemma2-10b-pt-224-keras | google/paligemma2-10b-pt-224-keras | google | 1.6 | low | |
| 298 | whisper-large-v3-turbo-lt | openai/whisper-large-v3-turbo | svogunas | 1.56 | low | |
| 299 | w2vbert-luganda-waxal-punct | sulaimank/w2vbert-luganda-waxal-stage2 | sulaimank | 1.52 | low | |
| 300 | CosyVoice2-0.5B | FunAudioLLM/CosyVoice2-0.5B | FunAudioLLM | 1.45 | high | Open-Source |
| 301 | MOSS-TTS-GGUF | — | OpenMOSS-Team | 1.32 | low | |
| 302 | MOSS-TTS-GGUF | — | niobures | 1.32 | low | |
| 303 | Fasih-TTS-V1 | coqui/XTTS-v2 | NightPrince | 1.3 | low | |
| 304 | w2v-bert-uk | facebook/w2v-bert-2.0 | Yehor | 1.3 | medium | |
| 305 | CosyVoice-300M-SFT | — | FunAudioLLM | 1.26 | low | Open-Source |
| 306 | CosyVoice-300M | FunAudioLLM/CosyVoice-300M | FunAudioLLM | 1.26 | low | Open-Source |
| 307 | CosyVoice-300M-Instruct | FunAudioLLM/CosyVoice-300M | FunAudioLLM | 1.26 | low | Open-Source |
| 308 | Fun-CosyVoice3-0.5B-2512 | FunAudioLLM/Fun-CosyVoice3-0.5B-2512 | FunAudioLLM | 1.21 | high | Open-Source |
| 309 | wav2vec2-xlsr-1b-finnish-lm-v2 | — | Finnish-NLP | 1.2 | high | |
| 310 | GLM-TTS | zai-org/GLM-TTS | zai-org | 1.12 | low | Open-source |
| 311 | whisper-tiny-ar-quran-mix-norm | openai/whisper-tiny | deepdml | 1.09 | medium | |
| 312 | MOSS-TTS | — | OpenMOSS-Team | 1.02 | low | Open‑source |
| 313 | MOSS-TTS-Local-Transformer | OpenMOSS-Team/MOSS-TTS-Local-Transformer | OpenMOSS-Team | 1.02 | low | Open‑source |
| 314 | MOSS-TTS-GGUF | — | OpenMOSS-Team | 1.02 | low | Open‑source |
| 315 | MOSS-TTS-GGUF | — | niobures | 1.02 | low | Open‑source |
| 316 | whisper-small-ar-quran-mix-norm | openai/whisper-small | deepdml | 0.6 | medium | |
| 317 | asr-whisper-large-v2-salt | openai/whisper-large-v2 | Sunbird | 0.5 | low | |