HF Model & Benchmark Matrix
Overview
Benchmarks
Speech
Models
Orgs
24,078 variants · 14,984 scores · 120 benchmarks
Home
/
Models
/
Chillarmo/ATOM
ATOM
Chillarmo/ATOM
kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
—
provider
Chillarmo
license
mit
language
hy
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
193
likes
1
created
—
last modified
2025-11-25T00:21:06+00:00
(2025)
huggingface
https://huggingface.co/Chillarmo/ATOM
tags
transformers
onnx
safetensors
whisper
automatic-speech-recognition
asr
audio
speech
low-resource
morpheme-tokenization
armenian
compact-model
generated_from_trainer
hy
dataset:Chillarmo/common_voice_20_armenian
arxiv:2212.04356
doi:10.57967/hf/7074
license:mit
model-index
endpoints_compatible
region:us
Benchmark scores (2)
benchmark
category
score
context
conf
evidence
WER
speech-asr
86.6
low
| Whisper-small | 244M | 86.6%* | +27.0% |
WER Common Voice
speech-asr
20.0
medium
Common Voice 20.0
Discussions (0)
none scraped.
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.