33 48 55

Steven Zheng

Steveeeeeeen

AI & ML interests

speech & audio

Recent Activity

new activity about 12 hours ago

all-hands/openhands-lm-32b-v0.1:Update library tag for better download tracking and code snippets!

new activity about 13 hours ago

senstella/csm-expressiva-1b:Change pipeline tag to Text-to-speech

updated a Space 1 day ago

Steveeeeeeen/SpeechLLM-Playbook

View all activity

Organizations

Steveeeeeeen's activity

upvoted a paper 8 days ago

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 10 days ago • 93

upvoted an article 10 days ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

13 days ago

• 140

upvoted a paper 28 days ago

Training and Inference Efficiency of Encoder-Decoder Speech Models

Paper • 2503.05931 • Published Mar 7 • 3

upvoted a paper about 1 month ago

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

Paper • 2503.04724 • Published Mar 6 • 69

upvoted 2 articles about 1 month ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 843

Article

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

Mar 7

• 52

upvoted 2 articles about 2 months ago

Article

SigLIP 2: A better multilingual vision language encoder

Feb 21

• 152

Article

Deploying Speech-to-Speech on Hugging Face

Oct 22, 2024

• 39

upvoted 2 collections about 2 months ago

OWLS: Scaling Laws for Speech Recognition and Translation

Collection

🦉 A suite of Whisper-style models from 250M to 18B parameters. Trained on up to 360K hours of data. 16k sampling rate. • 7 items • Updated Mar 10 • 5

Open Whisper-style Speech Models (OWSM)

Collection

Fully open Whisper-style speech foundation models developed by CMU WAVLab: https://www.wavlab.org/activities/2024/owsm/ • 15 items • Updated Feb 6 • 5

upvoted 2 papers about 2 months ago

Slamming: Training a Speech Language Model on One GPU in a Day

Paper • 2502.15814 • Published Feb 19 • 69

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19 • 181

upvoted an article about 2 months ago

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

Jan 23

• 171

upvoted a paper about 2 months ago

Presumed Cultural Identity: How Names Shape LLM Responses

Paper • 2502.11995 • Published Feb 17 • 10

upvoted an article about 2 months ago

Article

Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥

Feb 18

• 96

upvoted a collection 2 months ago

Feb 14 Releases 💌

Collection

23 items • Updated Feb 14 • 7

upvoted an article 2 months ago

Article

1 Billion Classifications

Feb 13

• 43