---
library_name: transformers.js
license: other
license_name: nyra-health-non-commercial-research
license_link: https://huggingface.co/nyralabs/CrisperWhisper2.0_turbo/blob/main/LICENSE.md
base_model: nyralabs/CrisperWhisper2.0_turbo
pipeline_tag: automatic-speech-recognition
tags:
  - onnx
  - whisper
  - verbatim
  - word-timestamps
---

# CrisperWhisper 2.0 Turbo — ONNX

ONNX export of [nyralabs/CrisperWhisper2.0_turbo](https://huggingface.co/nyralabs/CrisperWhisper2.0_turbo)
(verbatim, multilingual speech recognition with word-accurate timing), in the
onnx-community / Optimum layout:

- `onnx/encoder_model{_fp16,_q4}.onnx` — mel encoder (`input_features [1, 128, T]` → `last_hidden_state`)
- `onnx/decoder_model_merged{_fp16,_q4}.onnx` — KV-cache merged decoder (`use_cache_branch`)
  **with `cross_attentions.{i}` outputs** for DTW word timestamps against the model's
  supervised alignment heads (`generation_config.json`)

Decoder prompt layout (the model was trained with mode tags **before** `<|startoftranscript|>`):

```
[verbatim_1][verbatim_2][verbatim_3][verbatim_4][verbatim_5] (<htx> hotwords <ehtx>)? <|startoftranscript|> <|lang|> <|transcribe|> <|notimestamps|>
```

Verbatim output keeps disfluencies as bracketed event tokens (`[UM]`, `[UH]`, `[laughter]`,
`[cough]`, ...). Intended mode uses `[intended_1..5]` tags instead. See the
[upstream model card](https://huggingface.co/nyralabs/CrisperWhisper2.0_turbo) and
[nyrahealth/CrisperWhisper](https://github.com/nyrahealth/CrisperWhisper) for details.

## License — READ BEFORE USE

These weights are a **Derivative Work** of `nyralabs/CrisperWhisper2.0_turbo` and are
distributed under the **Nyra Health Non-Commercial Research License** (see `LICENSE.md`
in this repository — identical to the upstream license). In short:

- **Non-commercial / research use only.** No production or operational deployment, and no
  use from which commercial gain is derived.
- **Share-alike.** Any further derivative must remain under this same license and may not
  be re-released under a permissive or commercial license.
- By downloading or using these files you agree to be bound by the terms of `LICENSE.md`.
- Commercial licensing: contact licensing@nyra-labs.com.

Conversion: Optimum `main_export` (task `automatic-speech-recognition-with-past`,
`output_attentions=True`), fp16 via onnxconverter-common (`keep_io_types=True`),
q4 via onnxruntime `MatMulNBitsQuantizer(bits=4, block_size=32, is_symmetric=True)`.