mms-300m-waxal-sna

Home/Models/waxal-benchmarking/mms-300m-waxal-sna

waxal-benchmarking/mms-300m-waxal-sna

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: facebook/mms-300m
provider: waxal-benchmarking
license: cc-by-nc-4.0
language: sna
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 463
likes: 0
created: —
last modified: 2026-06-05T22:41:19+00:00 (2026)
huggingface: https://huggingface.co/waxal-benchmarking/mms-300m-waxal-sna
tags: transformerssafetensorswav2vec2automatic-speech-recognitionafrican-languageswaxalwaxalnetsnadataset:waxal-benchmarking/waxalarxiv:2606.02375base_model:facebook/mms-300mbase_model:finetune:facebook/mms-300mlicense:cc-by-nc-4.0endpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
WER	speech-asr	100.0		low	`\| 5.7817 \| 1.1990 \| 500 \| 2.8857 \| 1.0 \| 1.0 \|`
CER	speech-asr	100.0		low	`\| 5.7817 \| 1.1990 \| 500 \| 2.8857 \| 1.0 \| 1.0 \|`
WER	speech-asr	25.0	Test WER	medium	`\| Test WER \| 25.0% \|`
WER	speech-asr	25.0	WER	medium	`\| WER \| 25.0% \|`
CER	speech-asr	4.3	Test CER	medium	`\| Test CER \| 4.3% \|`
CER	speech-asr	4.3	CER	medium	`\| CER \| 4.3% \|`

none scraped.