Zipformer-cr-ctc-transducer-XL-290M

Home/Models/soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M

soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: —
provider: soundsgoodai
license: cc-by-nc-4.0
language: en
context: —
library: k2
vRAM (GB): —
size on disk: —
downloads: 157
likes: 1
created: —
last modified: 2026-07-19T01:57:27+00:00 (2026)
huggingface: https://huggingface.co/soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M
tags: k2automatic-speech-recognitionspeechaudiozipformertransducercr-ctck2-fsaoffline-asrendataset:esb/datasetsarxiv:2310.11230arxiv:2410.05101license:cc-by-nc-4.0eval-resultsregion:us

benchmark	category	score	context	conf	evidence
WER AMI	speech-asr	78.0	AMI Meeting Corpus	medium	`\| AMI Meeting Corpus \| 78.0 \| ESB datasets \|`
WER	speech-asr	11.3		low	`\| AMI \| 11.30 \|`
WER AMI	speech-asr	11.3	AMI	medium	`\| AMI \| 11.30 \|`
WER GigaSpeech	speech-asr	8.41	GigaSpeech	medium	`\| GigaSpeech \| 8.41 \|`
WER Earnings-22	speech-asr	7.64	Earnings22	medium	`\| Earnings22 \| 7.64 \|`
WER VoxPopuli	speech-asr	5.6	VoxPopuli	medium	`\| VoxPopuli \| 5.60 \|`
WER	speech-asr	5.56	Average WER	medium	`\| Average WER \| 5.56 \|`
WER LibriSpeech	speech-asr	3.01	LibriSpeech Other	medium	`\| LibriSpeech Other \| 3.01 \|`
WER SPGISpeech	speech-asr	1.64	SPGISpeech	medium	`\| SPGISpeech \| 1.64 \|`
WER LibriSpeech	speech-asr	1.31	LibriSpeech Clean	medium	`\| LibriSpeech Clean \| 1.31 \|`

none scraped.