DualTurn: Learning Turn-Taking from Dual-Channel Generative Speech Pretraining
Shangeth Rajaa
shangeth
AI & ML interests
Speech Representation Learning, Multi-Modal LLM, Spoken Dialogue Systems, Speech Synthesis
Recent Activity
updated a model 4 days ago
shangeth/Wren-ASR-0.5B-multi updated a Space 7 days ago
shangeth/Wren-ASR-0.5B-multi-demo published a Space 7 days ago
shangeth/Wren-ASR-0.5B-multi-demoOrganizations
Wren: A Family of Small Open-Weight Models for Unified Speech-Text Modelling
-
shangeth/Wren-TTS-0.5B-multi-expressive
Text-to-Speech • 0.5B • Updated • 125 -
Wren-TTS-0.5B-multi-expressive
🎭Expressive multilingual voice-cloning TTS — 23 style tags
-
shangeth/Wren-TTS-0.5B-multi
Text-to-Speech • 0.5B • Updated • 139 -
Wren-TTS-0.5B-multi
🐦Multilingual voice-cloning TTS — 8 languages
DualTurn: Learning Turn-Taking from Dual-Channel Generative Speech Pretraining
Wren: A Family of Small Open-Weight Models for Unified Speech-Text Modelling
-
shangeth/Wren-TTS-0.5B-multi-expressive
Text-to-Speech • 0.5B • Updated • 125 -
Wren-TTS-0.5B-multi-expressive
🎭Expressive multilingual voice-cloning TTS — 23 style tags
-
shangeth/Wren-TTS-0.5B-multi
Text-to-Speech • 0.5B • Updated • 139 -
Wren-TTS-0.5B-multi
🐦Multilingual voice-cloning TTS — 8 languages
spaces 4
Sleeping
Agents
Wren-ASR-0.5B-multi
🐦
Multilingual ASR — 8 languages
Running
Agents
Wren-TTS-0.5B-multi-expressive
🎭
Expressive multilingual voice-cloning TTS — 23 style tags
Running
Agents
Wren-TTS-0.5B-multi
🐦
Multilingual voice-cloning TTS — 8 languages
Running
Agents
Wren-TTS-360M-en
🐦
Voice-cloning TTS — Mimi codec + SmolLM2-360M (English)
models 7
shangeth/Wren-ASR-0.5B-multi
Automatic Speech Recognition • 0.5B • Updated • 86 • 1
shangeth/Wren-TTS-0.5B-multi
Text-to-Speech • 0.5B • Updated • 139
shangeth/Wren-TTS-360M-en
Text-to-Speech • 0.4B • Updated • 148
shangeth/Wren-TTS-0.5B-multi-expressive
Text-to-Speech • 0.5B • Updated • 125
shangeth/phi3-mini-ta_en
Translation • 4B • Updated • 1
shangeth/speechllm-2B
Feature Extraction • 2B • Updated • 2
shangeth/SpeechLLM
Feature Extraction • 2B • Updated • 19
datasets 10
shangeth/expresso-mimi-codes-tagged
Viewer • Updated • 25.7k • 91
shangeth/expresso-mimi-codes
Viewer • Updated • 27.5k • 213 • 1
shangeth/expresso
Viewer • Updated • 27.5k • 665
shangeth/mls-mimi-codes
Viewer • Updated • 1.47M • 952
shangeth/jenny-mimi-codes
Viewer • Updated • 21k • 241
shangeth/vctk-mimi-codes
Viewer • Updated • 44.3k • 103
shangeth/libritts-r-mimi-codes
Viewer • Updated • 375k • 256
shangeth/librispeech-mimi-codes
Viewer • Updated • 292k • 90
shangeth/ljspeech-mimi-codes
Viewer • Updated • 13.1k • 251
shangeth/libriasr-mimi-codes
Preview • Updated • 161