CrisperWhisper2.0_large

About

What CrisperWhisper2.0_large is

CrisperWhisper 2.0 [](https://pypi.org/project/crisperwhisper/) The most accurate verbatim speech recognition you can run in production: controllable, multilingual, and timed to the word. Release post · Paper · Full documentation · Models · Benchmark · Benchmark repo Most speech-to-text systems never actually decide whether to write down what was said or what was meant. They inherit that choice from their training data and apply it inconsistently. CrisperWhisper 2.0 makes it an explicit, controllable choice. One recording, two transcripts: Verbatim, exactly what was said, in one consistent format: [um] so we we need to, to reschedule the th- thursday meeting to [uh] march third at nine thirty [laughter] Intended, the clean version the speaker meant, with numbers, dates, and emails formatted the way you'd write them: So we need to reschedule the Thursday meeting to March 3 at 9:30. On top of that: - Word-level timings. Around 30 ms mean boundary error on read speech and 41 ms on conversational speech, the most precise word timing of any system we benchmarked, on both. - Verbatimize. Upgrade transcripts you already have: given audio plus a trusted clean transcript, the model reproduces your content word-for-word and inserts only the disfluencies and vocal events actually present in the audio (rare-word recall jumps from 6.8% to 96.1% vs. re-transcribing). This turns the world's abundant clean corpora into verbatim ones, ready for TTS data, clinical speech analysis, and dataset construction. - Multilingual. Verbatim and intended modes work across most languages Whisper supports. CrisperWhisper 2.0 tops the Nyra Verbatim Speech Benchmark leaderboard for disfluency F1 across ten languages, ahead of every closed-source alternative we tested. - Seamless longform. Audio of any length, transcribed without the usual chunk-boundary artifacts: each window continues from the words already transcribed (conditional continuation), so there are no duplicated or dropped words at the seams and no fragile timestamp-token bookkeeping. - Production inference. A CTranslate2 runtime with speculative decoding and built-in mitigation of Whisper's looping-hallucination failure mode. Perfo

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How audio & music work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys crisperwhisper2-0-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (crisperwhisper2-0-large below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="crisperwhisper2-0-large" -F file=@audio.mp3

Details

Languages, data & research

Papers

Licence

Commercial licence needed

Sources

Weights & code

Explore

More audio & music