🏗️ Building on HF

Steven

Steveeeeeeen

huggingface

·

AI & ML interests

speech & audio

Recent Activity

liked a Space 4 days ago

huggingface/moe-blogpost

updated a dataset 14 days ago

Steveeeeeeen/whisper-leaderboard-evals

updated a Space 17 days ago

hf-audio/README

View all activity

Organizations

liked a Space 4 days ago

The Ultimate MoE Training Handbook

A hands-on guide to training Mixture-of-Experts models

liked a Space 19 days ago

Jev Decision Index

Benchmarks and news on various repros of TypeSafe's Jev

liked a Space 20 days ago

Phonon

Text-to-speech that runs in your browser

liked a model 20 days ago

gradium/phonon-voices

Updated 21 days ago • 37

liked a Space 20 days ago

Speech to Decisions with Granite

Live speech, heard and sized up by one Granite Switch model

liked a Space 27 days ago

Drama 3

Direct Fish Audio Drama 3, streaming on ZeroGPU

liked 2 Spaces about 1 month ago

NeuDecide

A 40mb voice-action model, running entirely on WASM.

Open TTS Leaderboard

TTS systems evaluated on objective metrics.

liked 3 Spaces 4 months ago

HF Realtime Voice

Realtime voice over WebSocket or WebRTC

An Open Realtime Voice You Can Actually Run Yourself

Generate real‑time spoken replies from your voice

Real World VoiceEQ Benchmark

Explore speech model rankings with interactive tables

liked a Space 5 months ago

FFASR Leaderboard

Far-Field ASR — clean / noisy / reverberant benchmark

liked a Space 6 months ago

nano-cohere-transcribe

Pure-PyTorch ASR for Cohere Transcribe (14 languages)

liked a model 7 months ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated Jun 22 • 336k • • 5.7k

liked a Space 7 months ago

Distilling 100B+ Models 40x Faster with TRL

TRL distillation for 100B+ teachers, 40x faster

liked a dataset 7 months ago

ArtificialAnalysis/VoxPopuli-Cleaned-AA

Viewer • Updated Feb 17 • 628 • 1.44k • 7

liked 2 models 7 months ago

merve/smol-vision

Image-Text-to-Text • Updated Aug 10 • 196

CohereLabs/cohere-transcribe-03-2026

Automatic Speech Recognition • 2B • Updated Oct 7 • 103k • • 1.24k

liked 2 Spaces 8 months ago

Cohere Multilingual ASR

Transcribe audio to text in multiple languages

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

Explore synthetic data experiments on a bookshelf visualization