Nos_ASR-wav2vec2-xls-r-300m-gl

Home/Models/proxectonos/Nos_ASR-wav2vec2-xls-r-300m-gl

proxectonos/Nos_ASR-wav2vec2-xls-r-300m-gl

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: facebook/wav2vec2-xls-r-300m
provider: proxectonos
license: apache-2.0
language: gl
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 173
likes: 0
created: —
last modified: 2026-07-20T09:05:30+00:00 (2026)
huggingface: https://huggingface.co/proxectonos/Nos_ASR-wav2vec2-xls-r-300m-gl
tags: safetensorswav2vec2audioautomatic-speech-recognitiongldataset:openslr/openslrdataset:mozilla-foundation/common_voice_17_0dataset:GTM-UVigo/FalAIdataset:google/fleursdataset:proxectonos/Nos_Parlaspeech-GLbase_model:facebook/wav2vec2-xls-r-300mbase_model:finetune:facebook/wav2vec2-xls-r-300mlicense:apache-2.0model-indexregion:us

benchmark	category	score	context	conf	evidence
WER Common Voice	speech-asr	17.0		medium	`Common Voice 17.0`
WER FLEURS	speech-asr	15.83	FLEURS	medium	`\| FLEURS \| 15.83 \| 5.08 \| 0.0091 \|`
WER	speech-asr	7.85		low	`\| Common Voice 17.0 \| 7.85 \| 1.66 \| 0.0085 \|`
WER Common Voice	speech-asr	7.85	Common Voice 17.0	medium	`\| Common Voice 17.0 \| 7.85 \| 1.66 \| 0.0085 \|`
CER	speech-asr	1.66		low	`\| Common Voice 17.0 \| 7.85 \| 1.66 \| 0.0085 \|`
RTF	speech-asr	0.85		low	`\| Common Voice 17.0 \| 7.85 \| 1.66 \| 0.0085 \|`

none scraped.