Sorry! fixed link now! Well they support Text, image and audio while most support one or two modalities.
E.g if you make music and can embed your files to search for samples by description or sound with your mouth. Or take a drawing of a monster and search for the sound that the monster makes for creating a game. The larger models generally provide better embeddings, but the embeddings generated by gpt models like qwen3.5 are generally poor. Their latest embedding-model versions are the Qwen3-vl-embedding, but they dont have 3 modalities.
Markus PRO
marksverdhei
AI & ML interests
Everything.
Recent Activity
replied to their post about 11 hours 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 3 days ago
Scaling Language-Centric Omnimodal Representation Learning reacted
to
their post with 🤯 3 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
replied to their post about 11 hours ago
reacted to their post with 🤯👀 3 days ago
Post
250
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: 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
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: 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
-
- 2 replies
posted an
update 3 days ago
Post
250
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: 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
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: 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
-
-
- 2 replies
replied to their post 19 days ago
The best part:
reacted to their post with 🤯😔🤝👍🧠➕😎🤗❤️👀🚀🔥 19 days ago
Post
1323
🤔 Many cultures penalize or look down upon self-celebratory behavior. One such example is liking your own post. So why do i do it? Two reasons:
1. I disagree that self-celebratory behavior is inherently bad.
2. On the Huggingface hub, if your post has 0 reactions, it takes TWO whole clicks to react instead of one. So it is actually a UI hack that lowers the bar to engage.
So if you see me reacting to to my own post and thing 'Ugh, this guy is so full of himself' you are only half correct 😆
Now behold as I perform this magic trick called "Exhausting all reaction options for increased visual engagement" so you don't have to click twice to react. You're welcome!
Follow this aspiring 🤗 HF Hub influencer for more half-serious bloat in your feed 😜
1. I disagree that self-celebratory behavior is inherently bad.
2. On the Huggingface hub, if your post has 0 reactions, it takes TWO whole clicks to react instead of one. So it is actually a UI hack that lowers the bar to engage.
So if you see me reacting to to my own post and thing 'Ugh, this guy is so full of himself' you are only half correct 😆
Now behold as I perform this magic trick called "Exhausting all reaction options for increased visual engagement" so you don't have to click twice to react. You're welcome!
Follow this aspiring 🤗 HF Hub influencer for more half-serious bloat in your feed 😜
-
- 1 reply
posted an
update 19 days ago
Post
1323
🤔 Many cultures penalize or look down upon self-celebratory behavior. One such example is liking your own post. So why do i do it? Two reasons:
1. I disagree that self-celebratory behavior is inherently bad.
2. On the Huggingface hub, if your post has 0 reactions, it takes TWO whole clicks to react instead of one. So it is actually a UI hack that lowers the bar to engage.
So if you see me reacting to to my own post and thing 'Ugh, this guy is so full of himself' you are only half correct 😆
Now behold as I perform this magic trick called "Exhausting all reaction options for increased visual engagement" so you don't have to click twice to react. You're welcome!
Follow this aspiring 🤗 HF Hub influencer for more half-serious bloat in your feed 😜
1. I disagree that self-celebratory behavior is inherently bad.
2. On the Huggingface hub, if your post has 0 reactions, it takes TWO whole clicks to react instead of one. So it is actually a UI hack that lowers the bar to engage.
So if you see me reacting to to my own post and thing 'Ugh, this guy is so full of himself' you are only half correct 😆
Now behold as I perform this magic trick called "Exhausting all reaction options for increased visual engagement" so you don't have to click twice to react. You're welcome!
Follow this aspiring 🤗 HF Hub influencer for more half-serious bloat in your feed 😜
-
- 1 reply
replied to their post 21 days ago
This image from qwen3 tts tech report visualizes how little data is actually inputted as the voice prompt when using the speaker embedding, yet it completely shapes how the audio comes out. Quite interesting indeed
posted an
update 21 days ago
Post
1682
# The most underrated feature of Qwen3-TTS: Voice embeddings! 🧑🦰💬
https://huggingface.co/collections/marksverdhei/qwen3-voice-embedding
Did you know that Qwen3 TTS actually utilizes voice embedding?
Your voice is turned into a vector of 1024 (or 2048) dimensions,
and based on this vector alone you can get your custom voice.
But the coolest part is that this means that you can use math to modify voices, average voices. You can swap gender, pitch, mix and match vocies, and even create an emotion space! This also enables semantic voice search!
The voice embedding model is actually just a tiny encoder with just a few million parameters. I've ripped it out of the voice embeding model so you can use the embedding model standalone. Check out my collection! :D
https://huggingface.co/collections/marksverdhei/qwen3-voice-embedding
Did you know that Qwen3 TTS actually utilizes voice embedding?
Your voice is turned into a vector of 1024 (or 2048) dimensions,
and based on this vector alone you can get your custom voice.
But the coolest part is that this means that you can use math to modify voices, average voices. You can swap gender, pitch, mix and match vocies, and even create an emotion space! This also enables semantic voice search!
The voice embedding model is actually just a tiny encoder with just a few million parameters. I've ripped it out of the voice embeding model so you can use the embedding model standalone. Check out my collection! :D
-
- 1 reply