Yuancheng Wang

Ph.D. student for speech at CUHKSZ; TTS, Audio, Speech LLM; Amphion, NaturalSpeech 3, MaskGCT.

[𝚐𝔪𝟾𝚡𝚡𝟾 @gm8xx8]

Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

paper: https://t.co/OESKnCYA38
demo: https://t.co/yz8DGDOi1c

[Amphion @realamphion]

🚀Introducing Emilia-Large: 200K+ Hours of Open-Source Speech Data!
We’re excited to release Emilia-Large, the largest TTS pretraining datasets! With 200K+ hours of multilingual speech data, fully open-source. It is ready to use for #TTS and #SpeechLM.

[Amphion @realamphion]

A cross-lingual voice cloning demo by MaskGCT

[Amphion @realamphion]

Samples: https://t.co/sZYG2nSVUc

[Amphion @realamphion]

🚀🚀🚀 A Zero-Shot TTS model MaskGCT (Masked Generative Codec Transformer) is open-sourced in Amphion now. Trained with Emilia. Only needs 5 sec speech to clone
Paper: https://t.co/OdoQ3niCeY
HF: https://t.co/2mCZA9GLzD
Discord: https://t.co/FvmcJ5pm6z

Watch the demo by MaskGCT

[Yuancheng Wang @yuancwang]

@mohamed17381489 @realamphion @xutan_tx Hi, since the codec is design for tts task, we only achieve vc by replacing speaker embedding in the codec decoder, we will improve it recently!

[Amphion @realamphion]

Amphion now supports the FACodec, which is the core component of NaturalSpeech3 and the pretrained checkpoints are released.

Paper: https://t.co/bVbwpcTXBo
Checkpoints: https://t.co/CpF3zDArVZ
Demo: https://t.co/uFWnNEb309
Code: https://t.co/wUvqBoCHiD

@xutan_tx @yuancwang