audioX-south-v1

Home/Models/jiviai/audioX-south-v1

jiviai/audioX-south-v1

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: —
provider: jiviai
license: apache-2.0
language: ta, te, kn, ml
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 281
likes: 8
created: —
last modified: 2025-07-30T08:57:23+00:00 (2025)
huggingface: https://huggingface.co/jiviai/audioX-south-v1
tags: safetensorswhisperautomatic-speech-recognitionaudiospeechmultilingualtateknmllicense:apache-2.0model-indexregion:us

benchmark	category	score	context	conf	evidence
WER	speech-asr	20.1		low	`\| Jivi AI \| AudioX \| 12.14 \| 18.66 \| 18.68 \| 21.79 \| 24.63 \| 17.61 \| 26.92 \| 20.1 \|`

none scraped.