collectiveai-team / crisperwhisper

Unofficial implementation of Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection

  • Public
  • 2.3K runs
  • Paper
Run with an API
Playground API Examples README Versions

Run time and cost

This model costs approximately $0.73 to run on Replicate, or 1 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 9 minutes. The predict time for this model varies significantly based on the inputs.

Readme

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.

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 Transcription: Transcribes every spoken word exactly as it is, including and differentiating fillers like “um” and “uh”.
  • 🔍 Filler Detection: Detects and accurately transcribes fillers.
  • 🛡️ Hallucination Mitigation: Minimizes transcription hallucinations to enhance accuracy.