HF Model & Benchmark Matrix

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

griot-nano-1

Qlerqly/griot-nano-1

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
—
provider
Qlerqly
license
cc-by-nc-sa-4.0
language
ak, dag, ee, en, gaa
context
—
library
pytorch
vRAM (GB)
—
size on disk
—
downloads
207
likes
2
created
—
last modified
2026-07-14T09:19:10+00:00 (2026)
huggingface
https://huggingface.co/Qlerqly/griot-nano-1
tags
pytorchsafetensorsconformerctcspeechghanaafrican-languagesautomatic-speech-recognitionakdageeengaadataset:ghananlpcommunity/ghana-english-asr-2700hrsdataset:ghananlpcommunity/twi-health-asr-gemini-500hrsdataset:ghananlpcommunity/twi-speech-text-multispeaker-16kdataset:intronhealth/afrispeech-200license:cc-by-nc-sa-4.0region:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr41.67low| ak | 21,435 | 19.27% | 41.67% |
CERspeech-asr19.27low| ak | 21,435 | 19.27% | 41.67% |

Discussions (0)

none scraped.

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