HF Model & Benchmark Matrix

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

gigaam-v3-e2e-ctc-gguf

memoravox/gigaam-v3-e2e-ctc-gguf

kind
gguf
quant
gguf (8-bit)
family
misc
modality
automatic-speech-recognition
root model
ai-sage/GigaAM-v3
provider
memoravox
license
mit
language
ru
context
—
library
transcribe.cpp
vRAM (GB)
—
size on disk
—
downloads
118
likes
0
created
—
last modified
2026-07-14T00:38:23+00:00 (2026)
huggingface
https://huggingface.co/memoravox/gigaam-v3-e2e-ctc-gguf
tags
transcribe.cppggufasrspeech-to-textgigaamconformerctcrussianautomatic-speech-recognitionruarxiv:2506.01192base_model:ai-sage/GigaAM-v3base_model:quantized:ai-sage/GigaAM-v3license:mitregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr5.5low| F32 | [gigaam-v3-e2e-ctc-F32.gguf](https://huggingface.co/handy-computer/gigaam-v3-e2e-ctc-gguf/resolve/main/gigaam-v3-e2e-ctc-F32.gguf) | 843 MB | 5.50% |

Discussions (0)

none scraped.

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