Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
| Date | Stars |
|---|---|
| 2026-07-24 | 994 |
| 2026-07-25 | 994 |
| 2026-07-28 | 1028 |
| 2026-07-30 | 1034 |
| 2026-08-06 | 1034 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
# CrisperWhisper 2.0 [](https://pypi.org/project/crisperwhisper/) [](LICENSE) **The most accurate verbatim speech recognition you can run in production: controllable, multilingual, and timed to the word.** [Release post](https://www.nyra-labs.com/crisperwhisper) · [Paper](https://arxiv.org/abs/2607.18934) · [Full documentation](DOCS.md) · [Models](https://huggingface.co/nyralabs) · [Benchmark](https://www.nyra-labs.com/research/nyra-verbatim-speech-benchmark) <a href="https://www.nyra-labs.com/crisperwhisper"> <img src="https://img.shields.io/badge/%E2%96%B6%20%20TRY%20IT%20NOW-2563eb?style=for-the-badge" alt="Try it now"> </a> 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](https://www.nyra-labs.com/research/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. ## Performance The [Nyra Verbatim Speech Benchmark](https://www.nyra-labs.com/research/nyra-verbatim-speech-benchmark) scores fillers, repetitions, cut-offs, and vocal sounds as separate, typed metrics. Its headline number is **disfluency F1**: how reliably a system writes down the disfluencies that were actually spoken, without inventing ones that weren't. Averaged over ten languages: | # | System | Disfluency F1 | |--:|--------|--------------:| | 1 | **CrisperWhisper 2.0 Pro** | **93.5** | | 2 | **CrisperWhisper 2.0** | **87.8** | | 3 | ElevenLabs Scribe v2 | 79.2 | | 4 | Microsoft MAI-Transcribe-1.5 | 77.5 | | 5 | CrisperWhisper 1.0\* | 64.8 | | 6 | Inworld STT | 59.5 | | 7 | xAI Grok Speech-to-Text | 42.8 | | 8 | Deepgram Nova-3 | 37.8 | | 9 | Fish Audio ASR | 35.0 | | 10 | AssemblyAI Universal-3 Pro | 30.5 | <sub>\* CrisperWhisper 1.0 is English/German-only; its average covers those two languages. English and German use human-labeled evaluation sets; the other eight languages use synthetic verbatim sets. Per-language breakdowns and how the metric is computed are in the [benchmark post](https://www.nyra-labs.com/re
Excerpt of 10,773 characters
Read on GitHub
35
3
2
Jürgen Fleiß · University of Graz · Austria
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bc7b016b4debdced, topic:speech-recognition, topic:asr, topic:whisper