HF Model & Benchmark Matrix

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

nemotron-speech-streaming-en-0.6b-gguf

memoravox/nemotron-speech-streaming-en-0.6b-gguf

kind
gguf
quant
gguf (8-bit)
family
nemotron
modality
automatic-speech-recognition
root model
nvidia/nemotron-speech-streaming-en-0.6b
provider
memoravox
license
other
language
en
context
—
library
transcribe.cpp
vRAM (GB)
—
size on disk
—
downloads
120
likes
0
created
—
last modified
2026-07-14T01:14:54+00:00 (2026)
huggingface
https://huggingface.co/memoravox/nemotron-speech-streaming-en-0.6b-gguf
tags
transcribe.cppggufasrspeech-to-textparakeetconformerrnntstreamingcache-awareautomatic-speech-recognitionenarxiv:2312.17279arxiv:2305.05084base_model:nvidia/nemotron-speech-streaming-en-0.6bbase_model:quantized:nvidia/nemotron-speech-streaming-en-0.6blicense:otherregion:us

Benchmark scores (7)

benchmarkcategoryscorecontextconfevidence
WER Earnings-22speech-asr12.52low| **WER (%)** | **6.93** | 11.73 | 12.52 | 9.66 | 2.32 | 4.84 | 2.97 | 3.50 | 7.91 |
WER AMIspeech-asr11.73low| **WER (%)** | **6.93** | 11.73 | 12.52 | 9.66 | 2.32 | 4.84 | 2.97 | 3.50 | 7.91 |
WER GigaSpeechspeech-asr9.66low| **WER (%)** | **6.93** | 11.73 | 12.52 | 9.66 | 2.32 | 4.84 | 2.97 | 3.50 | 7.91 |
WER VoxPopulispeech-asr7.91low| **WER (%)** | **6.93** | 11.73 | 12.52 | 9.66 | 2.32 | 4.84 | 2.97 | 3.50 | 7.91 |
WERspeech-asr6.93**WER (%)**medium| **WER (%)** | **6.93** | 11.73 | 12.52 | 9.66 | 2.32 | 4.84 | 2.97 | 3.50 | 7.91 |
WER TED-LIUMspeech-asr3.5low| **WER (%)** | **6.93** | 11.73 | 12.52 | 9.66 | 2.32 | 4.84 | 2.97 | 3.50 | 7.91 |
WERspeech-asr2.31low| F32 | [nemotron-speech-streaming-en-0.6b-F32.gguf](https://huggingface.co/handy-computer/nemotron-speech-streaming-en-0.6b-gguf/resolve/main/nemotron-speech-streaming-en-0.6b-F32

Discussions (0)

none scraped.

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