Steven Zheng's picture

Steven Zheng PRO

Steveeeeeeen

·

AI & ML interests

speech & audio

Recent Activity

updated a dataset 3 days ago

Steveeeeeeen/whisper-leaderboard-evals

liked a model 6 days ago

LiquidAI/LFM2-Audio-1.5B

upvoted a paper 8 days ago

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

View all activity

Organizations

Steveeeeeeen 's Spaces 15

Running on Zero

Zonos

Generate audio from text with customizable emotions and settings

Open ASR Leaderboard Longform

Display and request speech recognition model benchmarks

Running on Zero

VibeVoice-Large

Generate a podcast audio from a script and voice samples

Open_ASR_Leaderboard

View and request model performance data

Running on Zero

Step Audio 2 Mini

Generate audio responses from text or voice input

TaDiCodec TTS AR Qwen2.5 0.5B

Generate speech from text with voice cloning

The SpeechLLM Playbook

🚧 [WiP] A deepdive into SpeechLLMs and Neural Audio Codec

Llasa 1b Multilingual TTS

Generate speech from text with or without cloning a voice

How Biased is Whisper?

Display and filter Whisper model evaluation results

Qwen2.5 Omni 7B

Greet someone by name

Talk To SmolVox

Talk to Fixie.ai's Ultravox with WebRTC ⚡️

Test

Chat with a friendly AI assistant

Talk To Ultravox

Talk to Fixie.ai's Ultravox with WebRTC ⚡️

Running on Zero

Llasagna v0.1 1b TTS

Generate customized speech from text using a reference audio

ASR Comparaison