HF Model & Benchmark Matrix

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

Inflect-Nano-v2

owensong/Inflect-Nano-v2

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
owensong/Inflect-Nano-v1
provider
owensong
license
apache-2.0
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
802
likes
120
created
—
last modified
2026-07-30T01:45:52+00:00 (2026)
huggingface
https://huggingface.co/owensong/Inflect-Nano-v2
tags
text-to-speechspeech-synthesislocal-ttscpuedge-aismall-modelbase-modelpytorchvits24khzenlicense:apache-2.0region:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
RTFspeech-asr15.93low| **Inflect-Micro-v2** | **0.1593** | **6.28×** |
UTMOSspeech-tts4.39low| **63.9%** | **4.386** | **4.21%** | **15.97 MB** | **10.72× real-time** |
WERspeech-asr4.21low| **63.9%** | **4.386** | **4.21%** | **15.97 MB** | **10.72× real-time** |

Discussions (0)

none scraped.

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