Open model
IBM Granite Speech
by IBM
IBM's Granite Speech models, released with open weights for speech recognition and speech translation.
- Self-hosted
Key figures
Every figure about IBM Granite Speech
Each figure is a row of a research dataset. Open it for the exact words of its source or the exact request it was read from.
Most Downloaded Speech Recognition Models (Hugging Face)
- ibm-granite/granite-4.0-1b-speechread October 19, 2026174,445 downloads
- ibm-granite/granite-speech-3.3-2bread October 19, 202652,510 downloads
- ibm-granite/granite-speech-3.3-8bread October 19, 20268,809 downloads
- ibm-granite/granite-speech-4.1-2b-plusread October 19, 202639,473 downloads
- ibm-granite/granite-speech-4.1-2bread October 19, 2026193,584 downloads
- ibm-granite/granite-speech-5.0-470m-turboctcread October 19, 202659,614 downloads
Other open models and engines
- Breeze ASRMediaTek Research
- CMU Sphinx (PocketSphinx)Carnegie Mellon University
- Cohere TranscribeCohere
- Coqui STTCoqui
- CrisperWhisperNyra Health
- Distil-WhisperHugging Face
- ESPnetESPnet developers
- faster-whisperSYSTRAN
- FluidAudioFluid Inference
- FunASRModelScope
- GigaAMSaluteDevices (Sber)
- GLM-ASRZ.ai
- IndicConformerAI4Bharat
- insanely-fast-whisperVaibhav Srivastav
- ivrit.ai Whisperivrit.ai
- JuliusJulius development team
- k2 and icefallNext-gen Kaldi team
- KaldiKaldi contributors
- KB-WhisperKBLab, National Library of Sweden
- Kotoba-WhisperKotoba Technologies
- Kyutai STTKyutai
- Lightning Whisper MLXMustafa Aljadery
- Meta MMSMeta AI
- MLX WhisperApple MLX team
- MoonshineMoonshine AI
- Mozilla DeepSpeechMozilla
- NB-WhisperNational Library of Norway AI Lab
- NVIDIA CanaryNVIDIA
- NVIDIA NeMoNVIDIA
- NVIDIA Nemotron Speech ASRNVIDIA