ESPnet

non-profit

https://github.com/espnet/espnet

Activity Feed Request to join this org

AI & ML interests

voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding

Recent Activity

JinchuanTian updated a model 2 days ago

espnet/bagpiper

JinchuanTian updated a collection 2 days ago

JinchuanTian updated a collection 2 days ago

View all activity

Papers

OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder

View all Papers

updated a model 2 days ago

espnet/bagpiper

Any-to-Any • Updated 2 days ago

updated a collection 2 days ago

Bagpiper

8 items • Updated 2 days ago

updated a dataset 2 days ago

espnet/Bagpiper_PreTrain_Data

Viewer • Updated 2 days ago • 29.4k • 13.3k

updated a collection 2 days ago

Bagpiper

8 items • Updated 2 days ago

updated 2 models 2 days ago

espnet/bagpiper-tts-sft

Text-to-Speech • Updated 2 days ago

espnet/bagpiper-sft

Any-to-Any • Updated 2 days ago

published 2 models 2 days ago

espnet/bagpiper-tts-sft

Text-to-Speech • Updated 2 days ago

espnet/bagpiper-sft

Any-to-Any • Updated 2 days ago

updated 2 datasets 2 days ago

espnet/Bagpiper_TTS_SFT_Data

Viewer • Updated 2 days ago • 738k • 31

espnet/Bagpiper_SFT_Data

Viewer • Updated 2 days ago • 2.67M • 334

published 2 datasets 2 days ago

espnet/Bagpiper_SFT_Data

Viewer • Updated 2 days ago • 2.67M • 334

espnet/Bagpiper_TTS_SFT_Data

Viewer • Updated 2 days ago • 738k • 31

authored 2 papers 4 days ago

Voice Memory for Agentic Speech Recognition

Paper • 2607.26410 • Published 6 days ago • 9

SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models

Paper • 2606.25990 • Published Jun 24