HF Model & Benchmark Matrix

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

nemotron-3.5-asr-streaming-0.6b-onnx-int4

onnx-community/nemotron-3.5-asr-streaming-0.6b-onnx-int4

kind
int4
quant
int4 (4-bit)
family
nemotron
modality
automatic-speech-recognition
root model
nvidia/nemotron-3.5-asr-streaming-0.6b
provider
onnx-community
license
mit
language
en, es, de, fr, it, ar, ja, ko, pt, ru, hi, zh
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
1,880
likes
18
created
—
last modified
2026-06-08T15:08:37+00:00 (2026)
huggingface
https://huggingface.co/onnx-community/nemotron-3.5-asr-streaming-0.6b-onnx-int4
tags
nemoonnxspeech-recognitioncache-aware ASRautomatic-speech-recognitionstreaming-asrmultilingualspeechaudioFastConformerRNNTParakeetASRpytorchNeMoenesdefritarjakopt

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
WER VoxPopulispeech-asr9.96high| 3 | es (es_419) | WER | 7.28 | 9.16 | 6.07 | 9.96 |
WER FLEURSspeech-asr7.28high| 3 | es (es_419) | WER | 7.28 | 9.16 | 6.07 | 9.96 |
WER MLSspeech-asr6.07high| 3 | es (es_419) | WER | 7.28 | 9.16 | 6.07 | 9.96 |

Discussions (0)

none scraped.

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