CrisperWhisper ⚠️ Deprecation notice CrisperWhisper (v1) is superseded by CrisperWhisper 2.0 and is no longer actively maintained. CrisperWhisper 2.0 has much better verbatim accuracy and 3 5x faster inference, keeps the crisp word level timestamps, and adds intended mode, hotwords, verbatimize, seamless longform, and speculative decoding. Install it with pip install crisperwhisper — the crisperwhisper package still runs this v1 model too, easing migration. Details: github.com/nyrahealth/CrisperWhisper. CrisperWhisper is an advanced variant of OpenAI's Whisper, designed for fast, precise, and verbatim speech recognition with accurate ( crisp ) word level timestamps. Unlike the original Whisper, which tends to omit disfluencies and follows more of a intended transcription style, CrisperWhisper aims to transcribe every spoken word exactly as it is, including fillers, pauses, stutters and false starts. Checkout our repo for more details: https://github.com/nyrahealth/CrisperWhisper Key Features 🎯 Accurate Word Level Timestamps : Provides precise timestamps, even around disfluencies and pauses, by utilizing an adjusted tokenizer and a custom attention loss during training. 📝 Verbatim…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy