Yatharth Sharma

YatharthS

·

AI & ML interests

TTS, speech generation, Agents, MCP

Recent Activity

reacted to theirpost with 🚀 about 23 hours ago

Open sourcing Coala Embeddings! It can compress 20 million documents which can take 80gb ram down to just 1gb RAM. Why is this important? Embeddings are used everywhere(RAG, semantic search, etc.) by many. Coala Embeddings massively cheapen cost to host them while being simply and easy to use. GitHub: https://github.com/ysharma3501/CoalaEmbeddings Notebook Demo: https://colab.research.google.com/drive/1TXip-vZg72e_2AB185MINufVVav8Oo9T?usp=sharing

reacted to theirpost with 🔥 1 day ago

Open sourcing Coala Embeddings! It can compress 20 million documents which can take 80gb ram down to just 1gb RAM. Why is this important? Embeddings are used everywhere(RAG, semantic search, etc.) by many. Coala Embeddings massively cheapen cost to host them while being simply and easy to use. GitHub: https://github.com/ysharma3501/CoalaEmbeddings Notebook Demo: https://colab.research.google.com/drive/1TXip-vZg72e_2AB185MINufVVav8Oo9T?usp=sharing

posted an update 1 day ago

Open sourcing Coala Embeddings! It can compress 20 million documents which can take 80gb ram down to just 1gb RAM. Why is this important? Embeddings are used everywhere(RAG, semantic search, etc.) by many. Coala Embeddings massively cheapen cost to host them while being simply and easy to use. GitHub: https://github.com/ysharma3501/CoalaEmbeddings Notebook Demo: https://colab.research.google.com/drive/1TXip-vZg72e_2AB185MINufVVav8Oo9T?usp=sharing

View all activity

Organizations

Posts 7

Post

1407

Open sourcing Coala Embeddings! It can compress 20 million documents which can take 80gb ram down to just 1gb RAM.

Why is this important? Embeddings are used everywhere(RAG, semantic search, etc.) by many.

Coala Embeddings massively cheapen cost to host them while being simply and easy to use.

GitHub: https://github.com/ysharma3501/CoalaEmbeddings
Notebook Demo: https://colab.research.google.com/drive/1TXip-vZg72e_2AB185MINufVVav8Oo9T?usp=sharing

Articles 2

Article

60

LLM based Audio models

View all Articles

spaces 4

LavaSR

Ultra fast universal speech enhancement model.

LuxTTS

Space for LuxTTS: a 150x realtime voice cloning TTS model

NovaSR

An incredibly fast and tiny audio upsampler

GLM ASR Nano

A space to transcribe audio files with the new sota GLM-ASR

models 8

YatharthS/CoalaEmbedding

Updated 1 day ago • 2

YatharthS/LavaSR

Audio-to-Audio • Updated Feb 27 • 924 • 84

YatharthS/LuxTTS

Text-to-Speech • Updated Jan 23 • 7.47k • 204

YatharthS/NovaSR

Audio-to-Audio • Updated Jan 19 • 73 • 87

YatharthS/LinaCodec

Audio-to-Audio • 0.1B • Updated Jan 3 • 27 • 24

YatharthS/FlashSR

Audio-to-Audio • Updated Dec 26, 2025 • 65

YatharthS/MiraTTS

Text-to-Speech • 0.5B • Updated Dec 24, 2025 • 326 • 191

YatharthS/LayaCodec

Audio-to-Audio • 0.1B • Updated Dec 14, 2025 • 23 • 14

datasets 0

None public yet