HF Model & Benchmark Matrix

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

qwen3-asr-0.6b-coreml

FluidInference/qwen3-asr-0.6b-coreml

kind
original
quant
bf16 (16-bit)
family
qwen
modality
automatic-speech-recognition
root model
Qwen/Qwen3-ASR-0.6B
provider
FluidInference
license
—
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
124
likes
12
created
—
last modified
2026-03-22T02:02:31+00:00 (2026)
huggingface
https://huggingface.co/FluidInference/qwen3-asr-0.6b-coreml
tags
coremlspeech-recognitionasrappleiosmacosqwenaudioautomatic-speech-recognitionenzhjakovithidmshiartrrudefres

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr4.4low| LibriSpeech test-clean (2620 files) | 4.4% | 1.9% | 2.8x |
WER LibriSpeechspeech-asr4.4LibriSpeech test-clean (2620 files)medium| LibriSpeech test-clean (2620 files) | 4.4% | 1.9% | 2.8x |
CERspeech-asr1.9low| LibriSpeech test-clean (2620 files) | 4.4% | 1.9% | 2.8x |

Discussions (0)

none scraped.

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