| 1 | wav2vec2-large-mms-1b-yoruba-testogbi | Speech Recognition | 2 | — | 2 | 965M |
| 2 | Voxtral-Small-24B-2507-FP8-dynamicRedHatAI | Speech Recognition | 2 | — | 2 | 24.3B |
| 3 | vakyansh-wav2vec2-bengali-bnm-200Harveenchadha | Speech Recognition | 2 | — | 2 | — |
| 4 | swin_large_patch4_window12_384.ms_in22ktimm | Image Classification | 2 | — | 2 | 232M |
| 5 | wav2vec2-large-xlsr-53-romaniangmihaila | Speech Recognition | 2 | — | 2 | — |
| 6 | wav2vec2-xls-r-1b-hebrewimvladikon | Speech Recognition | 2 | — | 2 | 963M |
| 7 | whisper-large-v3-turbo-et-subsTalTechNLP | Speech Recognition | 2 | — | 2 | 875M |
| 8 | odia_large_wav2vec2Harveenchadha | Speech Recognition | 2 | — | 2 | — |
| 9 | Replete-Coder-Instruct-8b-Merged-GGUFbartowski | Text Generation | 2 | — | 2 | — |
| 10 | whisper-large-v3-turkish-generalturkmedstt | Speech Recognition | 2 | — | 2 | 1.5B |
| 11 | wav2vec2-large-xlsr-pa-INdanurahul | Speech Recognition | 2 | — | 2 | — |
| 12 | whisper-large-v3-urdukingabzpro | Speech Recognition | 2 | — | 2 | 1.5B |
| 13 | kokoro-voices-GGUFcstr | Text to Speech | 2 | — | 2 | — |
| 14 | wav2vec2-large-xlsr-turkishcahya | Speech Recognition | 2 | — | 2 | — |
| 15 | wav2vec2-large-xlsr-53-swalokmatta | Speech Recognition | 2 | — | 2 | — |
| 16 | moonshine-base-komoonshine-ai | Speech Recognition | 2 | — | 2 | 61.5M |
| 17 | whisper-kannada-mediumvasista22 | Speech Recognition | 2 | — | 2 | — |
| 18 | gemma-3n-E4B-it-absolute-heresy-MPOA-GGUFmradermacher | Speech Recognition | 2 | — | 2 | — |
| 19 | Qwen3-ASR-1.7B-Q4_K_M-GGUFforyoung365 | Speech Recognition | 2 | — | 2 | — |
| 20 | whisper-large-v3-turbo-hr-parlaGoranS | Speech Recognition | 2 | — | 2 | 809M |
| 21 | whisper-baselitert-community | Speech Recognition | 2 | — | 2 | — |
| 22 | wav2vec2-large-mms-1b-somaliaskydheere | Speech Recognition | 2 | — | 2 | 965M |
| 23 | Phi-4-multimodal-instructLexius | Speech Recognition | 2 | — | 2 | 5.6B |
| 24 | nemotron-3.5-asr-streaming-0.6b-8bitmlx-community | Speech Recognition | 2 | — | 2 | 239M |
| 25 | wav2vec2-large-xlsr-indonesianGaluh | Speech Recognition | 2 | — | 2 | — |
| 26 | azerbaijani-whisper-smallLocalDoc | Speech Recognition | 2 | — | 2 | 242M |
| 27 | wav2vec2-large-xlsr-vietnameseNhut | Speech Recognition | 2 | — | 2 | — |
| 28 | ZONOS2-GGUFZyphra | Text to Speech | 2 | — | 2 | — |
| 29 | wav2vec2-large-xlsr-kinyarwanda-apostrophiedlucio | Speech Recognition | 2 | — | 2 | 315M |
| 30 | Qwen3-ASR-Nepalisidskarki | Speech Recognition | 2 | — | 2 | 2B |
| 31 | moss-transcribe-diarize-litertLuigi | Speech Recognition | 2 | — | 2 | — |
| 32 | wav2vec2-large-danish-npsc-nstNbAiLab | Speech Recognition | 2 | — | 2 | 315M |
| 33 | hubert-large-ls960-ftXenova | Speech Recognition | 2 | — | 2 | — |
| 34 | stt_it_fastconformer_hybrid_large_pcnvidia | Speech Recognition | 2 | — | 2 | — |
| 35 | wav2vec2-large-xlsr-53_nia12_phone-pinyin_chinesesnu-nia-12 | Speech Recognition | 2 | — | 2 | — |
| 36 | w2v-bert-2.0-srSagicc | Speech Recognition | 2 | — | 2 | 606M |
| 37 | gemma-3n-E4B-it-absolute-heresy-i1-GGUFmradermacher | Speech Recognition | 2 | — | 2 | — |
| 38 | nb-whisper-medium-betaNbAiLab | Speech Recognition | 2 | — | 2 | 764M |
| 39 | gemma-3n-E4B-it-PaperWitch-heresy-i1-GGUFmradermacher | Speech Recognition | 2 | — | 2 | — |
| 40 | wav2vec2-large-xlsr-punjabimanandey | Speech Recognition | 2 | — | 2 | 316M |
| 41 | parakeet-ctc-0.6bmlx-community | Speech Recognition | 2 | — | 2 | 609M |
| 42 | kb-whisper-tinyKBLab | Speech Recognition | 2 | — | 2 | 57.7M |
| 43 | KazakhTTS-OmniVoiceshyngys879 | Text to Speech | 2 | — | 2 | 613M |
| 44 | moonshine-tiny-ar-ONNXonnx-community | Speech Recognition | 2 | — | 2 | — |
| 45 | example-re-textclf-tacredpie | — | 2 | — | 2 | — |
| 46 | faster-whisper-tiny.enguillaumekln | Speech Recognition | 2 | — | 2 | — |
| 47 | mandarin-wav2vec2-aishell1kehanlu | Speech Recognition | 2 | — | 2 | — |
| 48 | whisper-tiny-ONNXonnx-community | Speech Recognition | 2 | — | 2 | — |
| 49 | gigaam-v3-GGUFcstr | Speech Recognition | 2 | — | 2 | — |
| 50 | wav2vec2-large-slavic-parlaspeech-hrclassla | Speech Recognition | 2 | — | 2 | 315M |