@yuancwang

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

hecheng0625.github.io
Joined March 2024
  • Tweets7
  • Following71
  • Followers17
Metis: A Foundation Speech Generation Model with Masked Generative Pre-training paper: arxiv.org/abs/2502.03128 demo: metis-demo.github.io
5
6
521
Yuancheng Wang retweeted
Amphion@realamphion26 Feb 2025
🚀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.
2
12
2
59
6,087
Yuancheng Wang retweeted
Amphion@realamphion24 Oct 2024
A cross-lingual voice cloning demo by MaskGCT
2
1
3
758
Yuancheng Wang retweeted
Amphion@realamphion25 Oct 2024
Samples: maskgct.github.io
1
1
380
Yuancheng Wang retweeted
Amphion@realamphion24 Oct 2024
🚀🚀🚀 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: arxiv.org/abs/2409.00750# HF: huggingface.co/spaces/amphio… Discord: discord.gg/fRaQpH7s Watch the demo by MaskGCT
8
32
5
75
11,694
Yuancheng Wang retweeted
Amphion@realamphion12 Mar 2024
Amphion now supports the FACodec, which is the core component of NaturalSpeech3 and the pretrained checkpoints are released. Paper: arxiv.org/abs/2403.03100 Checkpoints: huggingface.co/amphion/natur… Demo: huggingface.co/spaces/amphio… Code: github.com/open-mmlab/Amphio… @xutan_tx @yuancwang

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec...

While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intricately...

arxiv.org
AK
@_akhaliq6 Mar 2024
Microsoft presents NaturalSpeech 3 Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering
1
15
1
68
21,547
Load more