Markus PRO
marksverdhei
AI & ML interests
Everything.
Recent Activity
replied to their post 1 day ago
The hidden gem of open-source embedding models: LCO-Embedding
for text, image AND audio!
I found this model after reading the recent Massive Audio Embedding Benchmark (MAEB) paper, as it blew the other models out of the water on day zero. I've been using it personally for about a week, and searching my files by describing music, sound effects or images is both practical and entertaining. Really underrated model, would highly recommend checking it out: https://huggingface.co/LCO-Embedding/LCO-Embedding-Omni-7B
PS: If you're looking you run this model on llama.cpp, i've gone ahead and quantized them for you here 👉 https://huggingface.co/collections/marksverdhei/lco-embedding-omni-gguf upvoted a paper 4 days ago
Scaling Language-Centric Omnimodal Representation Learning reacted
to
their post with 🤯 4 days ago
The hidden gem of open-source embedding models: LCO-Embedding
for text, image AND audio!
I found this model after reading the recent Massive Audio Embedding Benchmark (MAEB) paper, as it blew the other models out of the water on day zero. I've been using it personally for about a week, and searching my files by describing music, sound effects or images is both practical and entertaining. Really underrated model, would highly recommend checking it out: https://huggingface.co/LCO-Embedding/LCO-Embedding-Omni-7B
PS: If you're looking you run this model on llama.cpp, i've gone ahead and quantized them for you here 👉 https://huggingface.co/collections/marksverdhei/lco-embedding-omni-gguf Organizations
-
unsloth/GLM-4.7-Flash-GGUF
Text Generation • 30B • Updated • 387k • 568 -
Qwen/Qwen3-TTS-12Hz-0.6B-Base
Text-to-Speech • Updated • 357k • 197 -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • Updated • 4.56M • • 2.86k -
Hexoplon/nb-whisper-large-distil-turbo-beta-ct2
Automatic Speech Recognition • Updated • 10 • 1
Old but gold AI classics
Standalone ECAPA-TDNN x-vector speaker encoders extracted from Qwen3-TTS. 1024-dim (0.6B) and 2048-dim (1.7B).
-
marksverdhei/Qwen3-Voice-Embedding-12Hz-0.6B
Feature Extraction • Updated • 3.45k • 19 -
marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B
Feature Extraction • Updated • 10.5k • 23 -
marksverdhei/Qwen3-Voice-Embedding-12Hz-0.6B-onnx
Feature Extraction • Updated • 21 -
marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B-onnx
Feature Extraction • Updated • 3
A collection of my FP8 quants for models missing this.
Old models from my thesis: https://www.duo.uio.no/handle/10852/96578
Standalone ECAPA-TDNN x-vector speaker encoders extracted from Qwen3-TTS. 1024-dim (0.6B) and 2048-dim (1.7B).
-
marksverdhei/Qwen3-Voice-Embedding-12Hz-0.6B
Feature Extraction • Updated • 3.45k • 19 -
marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B
Feature Extraction • Updated • 10.5k • 23 -
marksverdhei/Qwen3-Voice-Embedding-12Hz-0.6B-onnx
Feature Extraction • Updated • 21 -
marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B-onnx
Feature Extraction • Updated • 3
-
unsloth/GLM-4.7-Flash-GGUF
Text Generation • 30B • Updated • 387k • 568 -
Qwen/Qwen3-TTS-12Hz-0.6B-Base
Text-to-Speech • Updated • 357k • 197 -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • Updated • 4.56M • • 2.86k -
Hexoplon/nb-whisper-large-distil-turbo-beta-ct2
Automatic Speech Recognition • Updated • 10 • 1
A collection of my FP8 quants for models missing this.
Old but gold AI classics
Old models from my thesis: https://www.duo.uio.no/handle/10852/96578