whatmodel.sh / stt / CrisperWhisper

CrisperWhisper

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

CrisperWhisper is an open-weights speech-to-text model from Nyra Health, released August 2024. Its published size is 1.61B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

CrisperWhisper v1 (CSV entry 'nyrahealth/CrisperWhisper', now redirected to nyralabs/CrisperWhisper). Card marks v1 deprecated/superseded by CrisperWhisper 2.0 (a different checkpoint, not merged). Weights CC-BY-NC-4.0. Params: HF safetensors total. Command uses the custom transformers fork the card requires.

47.2±2.5#111 of 162 speech-to-text modelsfrom 3 benchmark results across 2 sources

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of CrisperWhisper, out of 176 with a score.

#modelscorewhereRAMreleased
122Distil-Whisper distil-large-v2 Hugging Face (Distil-Whisper)48±2local~2.3GB2023-10
123Distil-Whisper distil-small.en Hugging Face (Distil-Whisper)48±4local~0.9GB2023-12
124CrisperWhisper Nyra Health47±3local~4.4GB2024-08
125VibeVoice-ASR-Streaming-7B Microsoft47±5local~17GB2026-09
126SpeechBrain Conformer (LargeScaleASR / Loquacious) SpeechBrain47±5local~2.8GB2025-02

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 98% of its score
testresultvs the others in its rundifficultycountswhy
AfriSpeech-MultiBench · 7-region African-accent mean WER66.2% ✎▃····▂···▂▆█ beats 0/11avg 46%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 41%typical
AfriSpeech-MultiBench · Parliament (legal domain) WER79.3% ✎▃▂····▂·▅·▃█ beats 0/12avg 52%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%sharp
Open ASR English short-form WER (March 2026)6.7% ✎▁▁▁▃··▁▁▂██▆ beats 65/86avg 8.2%▇▇▇▇▇▇▇▇▇ 22%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~4.36 GB · from huggingface.co/nyralabs (official)
    uv run --with 'transformers @ git+https://github.com/nyrahealth/transformers.git@crisper_whisper' --with torch python -c "from transformers import pipeline; print(pipeline('automatic-speech-recognition', model='nyrahealth/CrisperWhisper', chunk_length_s=30)('audio.wav')['text'])"

Official weights and documentation: huggingface.co/nyralabs ↗

$ how the score was worked out · AfriSpeech-MultiBench (arXiv:… 76%, Open ASR Leaderboard 22%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suite2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 76%CC BY 4.0
Open ASR Leaderboard1▇▇▇▇▇▇▇ 22%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 47.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json