Views
No views yet
This is a mirror of the original weights for use with TTSDB.Original weights: https://huggingface.co/amphion/MaskGCT Original code: https://github.com/open-mmlab/Amphion
1@article{wang2024maskgct,
2 title={MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer},
3 author={Wang, Yuancheng and Zhan, Haoyue and Liu, Liwei and Zeng, Ruihong and Guo, Haotian and Zheng, Jiachen and Zhang, Qiang and Zhang, Xueyao and Zhang, Shunsi and Wu, Zhizheng},
4 journal={arXiv preprint arXiv:2409.00750},
5 year={2024}
6}1@inproceedings{amphion,
2 author={Zhang, Xueyao and Xue, Liumeng and Gu, Yicheng and Wang, Yuancheng and Li, Jiaqi and He, Haorui and Wang, Chaoren and Song, Ting and Chen, Xi and Fang, Zihao and Chen, Haopeng and Zhang, Junan and Tang, Tze Ying and Zou, Lexiao and Wang, Mingxuan and Han, Jun and Chen, Kai and Li, Haizhou and Wu, Zhizheng},
3 title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit},
4 booktitle={{IEEE} Spoken Language Technology Workshop, {SLT} 2024},
5 year={2024}
6}pip install ttsdb-maskgct1from ttsdb_maskgct import MaskGCT
2
3# Load the model (downloads weights automatically)
4model = MaskGCT(model_id="ttsds/MaskGCT")
5
6# Synthesize speech
7audio, sample_rate = model.synthesize(
8 text="Hello, this is a test of MaskGCT.",
9 reference_audio="path/to/reference.wav",
10 text_reference="Transcript of the reference audio.",
11 language="en",
12)
13
14# Save the output
15model.save_audio(audio, sample_rate, "output.wav")| Property | Value |
|---|---|
| Sample Rate | 24000 Hz |
| Parameters | 1010M |
| Architecture | Non-Autoregressive Masked Transformer |
| Languages | English, Chinese, Korean, Japanese, French, German |
| Release Date | 2024-10-17 |