wav2vec2-xls-r-300m-ftspeech

Home/Models/saattrupdan/wav2vec2-xls-r-300m-ftspeech

saattrupdan/wav2vec2-xls-r-300m-ftspeech

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: facebook/wav2vec2-xls-r-300m
provider: saattrupdan
license: other
language: da
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 518,397
likes: 0
created: —
last modified: 2023-09-11T13:27:55+00:00 (2023)
huggingface: https://huggingface.co/saattrupdan/wav2vec2-xls-r-300m-ftspeech
tags: transformerspytorchsafetensorswav2vec2automatic-speech-recognitiondadataset:ftspeechbase_model:facebook/wav2vec2-xls-r-300mbase_model:finetune:facebook/wav2vec2-xls-r-300mlicense:othermodel-indexendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
WER	speech-asr	20.48		low	`\| [Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train) \| 20.48 \| 17.91 \|`
WER Common Voice	speech-asr	20.48	[Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train)	medium	`\| [Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train) \| 20.48 \| 17.91 \|`
WER Common Voice	speech-asr	8.0		medium	`Common Voice 8.0`

none scraped.