Pinned

1. Mobile-Env Mobile-Env Public

   A Universal Platform for Training and Evaluation of Mobile Interaction

   Python 23 3

2. WebSRC WebSRC Public

   [EMNLP 2021] WebSRC: A dataset for web based structural machine reading comprehension.

   CSS 4

3. MSDWILD MSDWILD Public

   [INTERSPEECH 2022] This dataset is designed for multi-modal speaker diarization and lip-speech synchronization in the wild.

   HTML 28 1

4. VoiceFlow-TTS VoiceFlow-TTS Public

   [ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

   Python 241 20