Nvidia STT Parakeet v3
huggingface.coNew in v3
- Automatic punctuation and capitalization
- Accurate word-level and segment-level timestamps
- Long audio transcription, supporting audio up to 24 minutes long with full attention (on A100 80GB) or up to 3 hours with local attention.
- Released under a permissive CC BY 4.0 license
- Now supports 25 Languages:
Bulgarian (bg), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hungarian (hu), Italian (it), Latvian (lv), Lithuanian (lt), Maltese (mt), Polish (pl), Portuguese (pt), Romanian (ro), Slovak (sk), Slovenian (sl), Spanish (es), Swedish (sv), Russian (ru), Ukrainian (uk)
If this is as fast as the English-only version of Parakeet, then this is gonna displace Whisper entirely!