pinned
Running
Agents
TheESPnetLeaderBoard
🥇
ESPnet Leaderboard
AI & ML interests
voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding
Recent Activity
Running on Zero
Agents
Forced alignment
📐
When each line was said, and how sure the model is
Running on Zero
Agents
POWSM-CTC
🐁
What you said in phones, IPA, from a phonetic model
Sleeping
Agents
MELD speech emotion recognition demo
🎭
Run speech model demos with a web interface
Running
Agents
Speaker verification
🔍
Are these two recordings the same speaker?
Running on Zero
Agents
OWSM-CTC v4
🎙
151 languages in, 25 translation targets out, fast
Running on Zero
Agents
1
Universal speech enhancement
🎧
One model for noise, reverb, any mics, any rate
Running
Agents
LJSpeech VITS
🗣
English text to speech with a VITS model
Running on Zero
Agents
OWSM v4
🌍
151 languages in, 25 translation targets out, promptable
Sleeping
Agents
MELD speech emotion recognition demo
🎭
Launch a web demo for speech models with Gradio
Running on Zero
Agents
11
OWSM V4 Demo
🌍
This is a demo for OWSM-V4 CTC and medium model.
Runtime error
Agents
Voice Assistant Demo
📊
Runtime error
Agents
SingingSDS
🎶
Generate text with a customizable interface
Runtime error
Agents
2
Svs
💻
Generate singing voice from lyrics, duration, and pitch
Sleeping
Agents
1
TTS
🌖
Greet someone by name
Sleeping
Agents
S2st
📉
Translate Spanish speech to English
Running
README
🐠