TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment | https://huggingface.co/papers/2602.23068
AI & ML interests
None defined yet.
Recent Activity
Papers
View all Papers spaces 5
pinned
Running on Zero
Agents
86
TADA
🎵
Generate voice‑cloned speech from a short audio prompt
pinned
Running
Featured
67
Expressive TTS Arena
🎤
Vote for the most expressive TTS voice
Running
Agents
9
SLM Judge Leaderboard
⚖
View SLM Judge leaderboard with sortable heatmap tables
Running
Agents
21
Real World VoiceEQ Benchmark
🎙
Explore and compare speech model leaderboards with audio samples
Running
Agents
8
RW-Voice EQ ASR
🎙
Explore and compare English speech‑recognition model performance
datasets 0
None public yet