Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Amphion Alpha Release #2

Merged
merged 2 commits into from
Nov 28, 2023
Merged

Amphion Alpha Release #2

merged 2 commits into from
Nov 28, 2023

Conversation

RMSnow
Copy link
Collaborator

@RMSnow RMSnow commented Nov 28, 2023

We release the alpha version of Amphion 🎉. The key features are as follows:

  • TTS: Text to Speech
    • Support FastSpeech2 and VITS
  • SVC: Singing Voice Conversion
  • TTA: Text to Audio
  • Vocoder
    • Support several GAN-based Vocoders including MelGAN, HiFi-GAN, NSF-HiFiGAN, BigVGAN, and APNet.
    • Provide the official implementation of Multi-Scale Constant-Q Transfrom Discriminator.
    • Release two vocoder checkpoints (see Amphion/pretrained/README.md): Amphion Speech HiFi-GAN and Amphion Singing BigVGAN.
  • Evaluation
    • Support 16 objective metrics (see Amphion/egs/metrics/README.md) about F0 Modeling, Energy Modeling, Intelligibility, Spectrogram Distortion, and Speaker Similarity.
  • Datasets
    • Support 15 academic datasets (see Amphion/egs/datasets/README.md).

Thanks to all the contributors including:

  • Xueyao Zhang* @RMSnow, Liumeng Xue* @lmxue, Yuancheng Wang* @HeCheng0625, and Yicheng Gu* @VocodexElysium (The Chinese University of Hong Kong, Shenzhen)
  • Xi Chen @ChenX17 (The Chinese University of Hong Kong, Shenzhen)
  • Zihao Fang @Adorable-Qin (The Chinese University of Hong Kong, Shenzhen)
  • Haopeng Chen @arsity (The Chinese University of Hong Kong, Shenzhen)
  • Lexiao Zou @Lokshaw-Chau (The Chinese University of Hong Kong, Shenzhen & Harbin Institute of Technology, Shenzhen)
  • Chaoren Wang @yuantuo666 (The Chinese University of Hong Kong, Shenzhen)
  • Jun Han (The Chinese University of Hong Kong, Shenzhen)
  • Kai Chen (Shanghai AI Lab & OpenMMLab)
  • Haizhou Li (The Chinese University of Hong Kong, Shenzhen)
  • Zhizheng Wu @zhizhengwu (The Chinese University of Hong Kong, Shenzhen & Shanghai AI Lab)

*: Equal Contributions.

Also, thanks to Shenzhen Research Institute of Big Data (SRIBD) for partially supporting computing and scholarships to Xueyao, Liumeng, Yuancheng.

@RMSnow RMSnow added enhancement New feature or request good first issue Good for newcomers labels Nov 28, 2023
@zhizhengwu zhizhengwu merged commit 9682d0c into open-mmlab:main Nov 28, 2023
lmxue pushed a commit to lmxue/Amphion that referenced this pull request Dec 1, 2023
SVC key features and recipe template
lmxue pushed a commit to lmxue/Amphion that referenced this pull request Dec 1, 2023
batched infer, contentvec 12 layers, fs based hop
@open-mmlab open-mmlab deleted a comment from PedramHaeri Dec 1, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request good first issue Good for newcomers
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants