HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

wav2vec2-base-760-turkish

ceyda/wav2vec2-base-760-turkish

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
facebook/wav2vec2-base
provider
ceyda
license
apache-2.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
360
likes
3
created
—
last modified
2023-03-25T13:13:19+00:00 (2023)
huggingface
https://huggingface.co/ceyda/wav2vec2-base-760-turkish
tags
transformerspytorchsafetensorswav2vec2automatic-speech-recognitionaudiospeechxlsr-fine-tuning-weektrdataset:common_voicelicense:apache-2.0model-indexendpoints_compatibleregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr22.6mediumWER: 22.6023
CERspeech-asr6.05mediumCER: 6.0541

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.