Gallil Maimon
gallilmaimon.bsky.social
Gallil Maimon
@gallilmaimon.bsky.social
PhD student @CseHuji; Audio Processing, Speech Language Modelling
Reposted by Gallil Maimon
@gallilmaimon.bsky.social and his team trained a Speech Language Models on 1xA5000 GPU in 24 hours
February 26, 2025 at 1:14 AM
Reposted by Gallil Maimon
I love papers that make ML training accessible with consumer GPUs. Great example: "Slamming: Training a Speech Language Model on One GPU in a Day" released 3 days ago. The full code and training data are available and reproducible using a 24GB RTX 3090.

- arxiv.org/abs/2502.15814
Slamming: Training a Speech Language Model on One GPU in a Day
We introduce Slam, a recipe for training high-quality Speech Language Models (SLMs) on a single academic GPU in 24 hours. We do so through empirical analysis of model initialisation and architecture, ...
arxiv.org
February 28, 2025 at 4:19 PM
🚨Attention #speech @hf.co people🤗💬
We added official support for mhubert-25hz from TWIST in transformers. We also converted it from fairseq to HF!

Check it out✌️
huggingface.co/slprl/mhuber...
slprl/mhubert-base-25hz · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 11, 2025 at 8:00 PM
I am thrilled to share that SALMon🍣 got accepted to #ICASSP25

For code, data, preprint and live leaderboard checkout - pages.cs.huji.ac.il/adiyoss-lab/...

w/ Amit Roth and Yossi Adi
December 21, 2024 at 6:11 AM
#Speech people: I am looking for examples (or resources) where stress or emphasis on a phrase changes the meaning of a sentence. This part of a study on intonation in SpeechLMs.

I gave a decent ChatGPT answer below, but many weren't great...
December 16, 2024 at 10:59 AM
We added SpiritLM to the SALMon🍣 leaderboard! Nice jump in emotion consistency, but still no improvement in jointly modelling text content and acoustics🥲
Think your SLM can do better?💪
links👇
November 28, 2024 at 8:39 AM
Reposted by Gallil Maimon
I've started putting together a starter pack with people working on Speech Technology and Speech Science: go.bsky.app/BQ7mbkA

(Self-)nominations welcome!
November 19, 2024 at 11:13 AM