HF Model & Benchmark Matrix

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

w2v-bert-2.0-afrivoices-ea-6l-asr-int8-edge

leophill/w2v-bert-2.0-afrivoices-ea-6l-asr-int8-edge

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
leophill/w2v-bert-2.0-afrivoices-ea-6l-asr
provider
leophill
license
cc-by-4.0
language
luo, kln, kik, mas, som, sw
context
—
library
ctranslate2
vRAM (GB)
—
size on disk
—
downloads
139
likes
2
created
—
last modified
2026-07-20T22:28:57+00:00 (2026)
huggingface
https://huggingface.co/leophill/w2v-bert-2.0-afrivoices-ea-6l-asr-int8-edge
tags
ctranslate2onnxaudioautomatic-speech-recognitionw2v-bert-2.0ctcint8kenlmafrican-languagesluoklnkikmassomswdataset:DigitalUmuganda/Afrivoice_Swahilidataset:DigitalUmuganda/Afrivoicedataset:Anv-ke/kikuyudataset:Anv-ke/Kalenjindataset:Anv-ke/Somalidataset:Anv-ke/Dholuodataset:Anv-ke/Maasaibase_model:leophill/w2v-bert-2.0-afrivoices-ea-6l-asrbase_model:quantized:leophill/w2v-bert-2.0-afrivoices-ea-6l-asr

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
RTFspeech-asr51.0mediumRTF 0.51
WERspeech-asr34.81mediumWER 0.3481

Discussions (0)

none scraped.

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