Catalogs

Models

372 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

Weights and source
Explore other catalogs
How to choose models

Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.

Understand our sources and data limits

  1. wav2vec2-xlsr-53-espeak-cv-ft facebook automatic speech recognition · License apache-2.0 · 406,468 downloads · by facebook Audio · Open weights 406k HF downloads
  2. Qwen3 ForcedAligner 0.6B Alibaba Multilingual forced alignment model that aligns speech and transcripts in 11 languages, predicting… Audio · Open weights 398k HF downloads
  3. nemotron-speech-streaming-en-0.6b nvidia automatic speech recognition · License other · 395,353 downloads · by nvidia Audio · Open weights 395k HF downloads
  4. vakyansh-wav2vec2-sanskrit-sam-60 Harveenchadha automatic speech recognition · 365,409 downloads · by Harveenchadha Audio · Open weights 365k HF downloads
  5. VoxCPM2 OpenBMB VoxCPM2 is OpenBMB’s open-source tokenizer-free multilingual text-to-speech model for natural speec… Audio · Open weights 365k HF downloads
  6. parakeet-ctc-1.1b nvidia automatic speech recognition · License cc-by-4.0 · 359,118 downloads · by nvidia Audio · Open weights 359k HF downloads
  7. wav2vec2-xlsr-khmer gagan3012 automatic speech recognition · License apache-2.0 · 358,844 downloads · by gagan3012 Audio · Open weights 359k HF downloads
  8. sanoTTS ampixa text to speech · License gpl-3.0 · 344,371 downloads · by ampixa Audio · Open weights 344k HF downloads
  9. speaker-diarization-3.1 pyannote automatic speech recognition · License mit · 7,271,569 downloads · by pyannote Audio · Open weights 34k HF downloads
  10. wav2vec2-xls-r-300m-sk-cv8 comodoro automatic speech recognition · License apache-2.0 · 339,397 downloads · by comodoro Audio · Open weights 339k HF downloads
  11. Qwen3-ASR-1.7B-hf Qwen automatic speech recognition · License apache-2.0 · 329,785 downloads · by Qwen Audio · Open weights 33k HF downloads
  12. whisper-large-v3-turbo-gguf handy-computer automatic speech recognition · License apache-2.0 · 328,382 downloads · by handy-computer Audio · Open weights 328k HF downloads
  13. Qwen3-TTS-12Hz-1.7B-VoiceDesign Qwen text to speech · License apache-2.0 · 328,077 downloads · by Qwen Audio · Open weights 328k HF downloads
  14. Qwen2-Audio-7B-Instruct Qwen audio text to text · License apache-2.0 · 316,774 downloads · by Qwen Audio · Open weights 317k HF downloads
  15. wav2vec2-large-xlsr-53-slovenian anton-l automatic speech recognition · License apache-2.0 · 315,716 downloads · by anton-l Audio · Open weights 316k HF downloads
  16. Qwen3-TTS-Tokenizer-12Hz Qwen audio to audio · License apache-2.0 · 314,115 downloads · by Qwen Audio · Open weights 314k HF downloads
  17. hubert-large-ls960-ft facebook automatic speech recognition · License apache-2.0 · 313,174 downloads · by facebook Audio · Open weights 313k HF downloads
  18. wav2vec2-large-xls-r-300m-bg-d2 DrishtiSharma automatic speech recognition · License apache-2.0 · 309,270 downloads · by DrishtiSharma Audio · Open weights 309k HF downloads
  19. indic-parler-tts ai4bharat text to speech · License apache-2.0 · 307,647 downloads · by ai4bharat Audio · Open weights 308k HF downloads
  20. whisper-large-v3-gguf handy-computer automatic speech recognition · License apache-2.0 · 307,339 downloads · by handy-computer Audio · Open weights 307k HF downloads
  21. whisper-medium openai automatic speech recognition · License apache-2.0 · 301,858 downloads · by openai Audio · Open weights 302k HF downloads
  22. seamless-m4t-v2-large facebook automatic speech recognition · License cc-by-nc-4.0 · 299,813 downloads · by facebook Audio · Open weights 3k HF downloads
  23. wav2vec2-large-xls-r-300m-sinhala-low-LR-part1 SpideyDLK automatic speech recognition · 296,727 downloads · by SpideyDLK Audio · Open weights 297k HF downloads
  24. whisper-large-v3-turbo mlx-community automatic speech recognition · 294,553 downloads · by mlx-community Audio · Open weights 295k HF downloads
  25. wav2vec2-large-mms-1b-azerbaijani-common_voice15.0 nijatzeynalov automatic speech recognition · License cc-by-nc-4.0 · 280,888 downloads · by nijatzeynalov Audio · Open weights 281k HF downloads
  26. parakeet-tdt-0.6b-v3-coreml FluidInference automatic speech recognition · License cc-by-4.0 · 280,547 downloads · by FluidInference Audio · Open weights 281k HF downloads
  27. tts-hifigan-libritts-22050Hz speechbrain text to speech · License apache-2.0 · 277,462 downloads · by speechbrain Audio · Open weights 277k HF downloads
  28. Higgs-Audio-v3-Studio drbaph text to speech · License other · 276,385 downloads · by drbaph Audio · Open weights 276k HF downloads
  29. whisper-small-mlx mlx-community automatic speech recognition · 273,584 downloads · by mlx-community Audio · Open weights 274k HF downloads
  30. wav2vec2-lv-60-espeak-cv-ft facebook automatic speech recognition · License apache-2.0 · 273,343 downloads · by facebook Audio · Open weights 273k HF downloads
  31. wav2vec2-large-xlsr-marathi sumedh automatic speech recognition · License apache-2.0 · 273,316 downloads · by sumedh Audio · Open weights 273k HF downloads
  32. mms-1b-all facebook automatic speech recognition · License cc-by-nc-4.0 · 266,668 downloads · by facebook Audio · Open weights 267k HF downloads
  33. wav2vec2-large-xlsr-53-punjabi kingabzpro automatic speech recognition · License apache-2.0 · 265,323 downloads · by kingabzpro Audio · Open weights 265k HF downloads
  34. canary-180m-flash-gguf handy-computer automatic speech recognition · License cc-by-4.0 · 265,303 downloads · by handy-computer Audio · Open weights 265k HF downloads
  35. Phi 4 multimodal Microsoft Phi 4 multimodal is Microsoft's 5.6B open-weight model that folds text, vision and speech into a si… Audio · Open weights 264k HF downloads
  36. MeloTTS-English myshell-ai text to speech · License mit · 263,685 downloads · by myshell-ai Audio · Open weights 264k HF downloads