Speech Recognition Community Event Version 2

non-profit

Activity Feed

AI & ML interests

Multi-Lingual Speech Recognition

Recent Activity

tuananh7198 authored a paper 24 days ago

PhoBERT: Pre-trained language models for Vietnamese

tuananh7198 authored a paper 24 days ago

BERTweet: A pre-trained language model for English Tweets

tuananh7198 authored a paper 24 days ago

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

View all activity

flozi00

posted an update 4 days ago

Post

202

Struggling with NVIDIA drivers on Ubuntu 24.04?
Can't use your GPUs with CUDA installed, or only half of them work?
Black screen after startup or nvidia-smi fails?

The nokaslr boot option might be the cause—and the solution.
Find out why disabling KASLR can fix these GPU issues until a permanent driver update is available.

https://flozi.net/en/guides/linux/solving-nvidia-driver-issues-on-ubuntu-24-04-with-nokaslr

flozi00

posted an update 9 days ago

Post

1922

I just got asked about the differences between Blackwell systems and Grace Blackwell systems. What's the difference and how much of a performance gap is there between them?

https://flozi.net/en/hardware/nvidia/benchmarks/b200-vs-gb200-efficiency-comparison

Here's a summary of the key points from the article:

GB200 (Grace Blackwell) is a Superchip: It integrates a Grace CPU and two Blackwell GPUs into a single package.
B200 is a GPU-only module: It's designed to be paired with x86 or ARM CPUs in more traditional server setups.

Performance and Efficiency:

Based on MLPerf Training v5.0 benchmarks, the article concludes:

GB200 systems are approximately 42% more efficient than B200 systems on average. This is especially true in large-scale deployments (100+ GPUs), where the GB200's integrated design and high-speed NVLink interconnect provide a significant advantage.

In smaller, single-node systems (e.g., 8 GPUs), the performance difference is much smaller, around 10-15%.

Use Cases:

Choose GB200 for large-scale AI clusters, training massive models, and when maximum efficiency is the top priority.

Choose B200 for smaller deployments, when you need the flexibility to choose your own CPU, or for mixed AI and HPC workloads.

flozi00

posted an update 12 days ago

Post

3110

Some weeks ago, i've just decide its time to leave LinkedIn for me.
It got silent around my open source activities the last year, so i thought something has to change.

That's why my focus will move to share experiences and insights about hardware, drivers, kernels and linux. I won't post about how to use models, built agents or do prompting. I want to share about some deeper layers the actual hypes are built on.

I will start posting summarizations of my articles here on the hub.

English version:
https://flozi.net/en

German translated version:
https://flozi.net/de

Feel free to reach me if you want to read something specific.

2 replies

tuananh7198

authored 4 papers 24 days ago

vumichien

authored 2 papers about 1 month ago

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources

Paper • 2509.25531 • Published Sep 29 • 7

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Paper • 2510.08697 • Published Oct 9 • 35

gagan3012

authored a paper about 1 month ago

Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models

Paper • 2510.06107 • Published Oct 7 • 2

sanchit-gandhi

authored 2 papers 4 months ago

Magistral

Paper • 2506.10910 • Published Jun 12 • 65

Voxtral

Paper • 2507.13264 • Published Jul 17 • 29

gagan3012

authored a paper 5 months ago

Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images

Paper • 2506.13458 • Published Jun 16

reach-vb

posted an update 5 months ago

Post

5684

Excited to onboard FeatherlessAI on Hugging Face as an Inference Provider - they bring a fleet of 6,700+ LLMs on-demand on the Hugging Face Hub 🤯

Starting today, you'd be able to access all those LLMs (OpenAI compatible) on HF model pages and via OpenAI client libraries too! 💥

Go, play with it today: https://huggingface.co/blog/inference-providers-featherless

P.S. They're also bringing on more GPUs to support all your concurrent requests!

1 reply

gagan3012

authored a paper 6 months ago

Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning

Paper • 2505.16088 • Published May 22 • 3

DrishtiSharma

authored a paper 6 months ago

Behind Maya: Building a Multilingual Vision Language Model

Paper • 2505.08910 • Published May 13 • 2

reach-vb

posted an update 6 months ago

Post

4594

hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥

as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!

in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.

p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage

p.p.s. this is fully backwards compatible so everything will work as it should! 🤗