CrisperWhisper

Home/Models/nyralabs/CrisperWhisper

CrisperWhisper

nyralabs/CrisperWhisper

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: openai/whisper-large-v3
provider: nyralabs
license: cc-by-nc-4.0
language: de, en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 31,360
likes: 337
created: —
last modified: 2026-07-22T12:07:48+00:00 (2026)
huggingface: https://huggingface.co/nyralabs/CrisperWhisper
tags: transformerssafetensorswhisperautomatic-speech-recognitiondeenarxiv:2408.16589arxiv:2110.13900base_model:openai/whisper-large-v3base_model:finetune:openai/whisper-large-v3license:cc-by-nc-4.0eval-resultsendpoints_compatibleregion:us

Benchmark scores (12)

benchmark	category	score	context	conf	evidence
WER Common Voice	speech-asr	80.0	[Common Voice](https://commonvoice.mozilla.org/en/datasets)	medium	`\| [Common Voice](https://commonvoice.mozilla.org/en/datasets) \| F1 Score \| 0.80 \| 0.42 \| 0.48 \|`
WER AMI	speech-asr	79.0	[AMI IHM](https://groups.inf.ed.ac.uk/ami/corpus/)	medium	`\| [AMI IHM](https://groups.inf.ed.ac.uk/ami/corpus/) \| F1 Score \| 0.79 \| 0.63 \| 0.66 \|`
WER Earnings-22	speech-asr	12.37	[Earnings22](https://huggingface.co/datasets/revdotcom/earnings22)	medium	`\| [Earnings22](https://huggingface.co/datasets/revdotcom/earnings22) \| 12.37 \| 11.3 \|`
WER GigaSpeech	speech-asr	10.27	[GigaSpeech](https://huggingface.co/datasets/speechcolab/gigaspeech)	medium	`\| [GigaSpeech](https://huggingface.co/datasets/speechcolab/gigaspeech) \| 10.27 \| 10.02 \|`
WER AMI	speech-asr	8.72	[AMI](https://huggingface.co/datasets/edinburghcstr/ami)	medium	`\| [AMI](https://huggingface.co/datasets/edinburghcstr/ami) \| 8.72 \| 16.01 \|`
WER VoxPopuli	speech-asr	8.61	[VoxPopuli](https://huggingface.co/datasets/facebook/voxpopuli)	medium	`\| [VoxPopuli](https://huggingface.co/datasets/facebook/voxpopuli) \| 8.61 \| 9.52 \|`
WER Common Voice	speech-asr	8.19	[CommonVoice](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0)	medium	`\| [CommonVoice](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0) \| 8.19 \| 9.67 \|`
WER	speech-asr	6.66	Average WER	medium	`\| Average WER \| 6.66 \| 7.7 \|`
WER LibriSpeech	speech-asr	3.97	[LibriSpeech other](https://huggingface.co/datasets/openslr/librispeech_asr)	medium	`\| [LibriSpeech other](https://huggingface.co/datasets/openslr/librispeech_asr) \| 3.97 \| 3.91 \|`
WER TED-LIUM	speech-asr	3.35	[TED-LIUM](https://huggingface.co/datasets/LIUM/tedlium)	medium	`\| [TED-LIUM](https://huggingface.co/datasets/LIUM/tedlium) \| 3.35 \| 3.9 \|`
WER SPGISpeech	speech-asr	2.71	[SPGISpeech](https://huggingface.co/datasets/kensho/spgispeech)	medium	`\| [SPGISpeech](https://huggingface.co/datasets/kensho/spgispeech) \| 2.71 \| 2.95 \|`
WER LibriSpeech	speech-asr	1.74	[LibriSpeech clean](https://huggingface.co/datasets/openslr/librispeech_asr)	medium	`\| [LibriSpeech clean](https://huggingface.co/datasets/openslr/librispeech_asr) \| 1.74 \| 2.03 \|`

Discussions (0)

none scraped.