gmltmd789

Ph.D. Candidate at Seoul National University, Republic of Korea. Interested in Spoken Language Model, Speech Synthesis, and Generative Model

Seoul National UniversitySeoul, Republic of Korea

Pinned Repositories

speech-trident
Awesome speech/audio LLMs, representation learning, and codec models
796 44 348
gmltmd789.github.io
Language:HTML0 1 00
UnitSpeech
An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"
Language:Jupyter Notebook133 11 913
AnyGPT
Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"
Language:Python801 20 4264
VoiceFlow-TTS
[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"
Language:Python323 15 1721
LibriSQA
33 1 21

gmltmd789's Repositories

gmltmd789/UnitSpeech
An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"
Language:Jupyter Notebook133 11 913
gmltmd789/gmltmd789.github.io
Language:HTML0 1 00