Amphion is a toolkit for Audio, Music, and Speech Generation. GitHub: https://xitter.cf/t.co/SDsdCO4M29 HF: https://xitter.cf/t.co/3VJSoumiFS
Joined December 2023
- Tweets59
- Following54
- Followers386
- Likes8
✨ What’s New?
- 2x Scale: Expanded the original Emilia dataset from 101K to 200K+ hours with the new Emilia-YODAS dataset.
- Low-Resource Boost: Enhanced support for languages like German, French, and Japanese.
- Commercial Use: Emilia-YODAS is released under CC-BY
Amphion retweeted
Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
paper: arxiv.org/abs/2502.03128
demo: metis-demo.github.io
Amphion retweeted
Sorry to interrupt but, YES, MaskGCT TTS works for French language !
I have not tested with other latin languages yet, but my guess is that it should work too 🤗
Fuck yeah! MaskGCT - New open SoTA Text to Speech model! 🔥
> Zero-shot voice cloning
> Emotional TTS
> Trained on 100K hours of data
> Long form synthesis
> Variable speed synthesis
> Bilingual - Chinese & English
> Available on Hugging Face
Fully non-autoregressive architecture:
> Stage 1: Predicts semantic tokens from text, using tokens extracted from a speech self-supervised learning (SSL) model
> Stage 2: Predicts acoustic tokens conditioned on the semantic tokens.
Synthesised: "Would you guys personally like to have a fake fireplace, an electric one, in your house? Or would you rather have a real fireplace? Let me know down below. Okay everybody, that's all for today's video and I hope you guys learned a bunch of furniture vocabulary!"
TTS scene keeps getting lit! 🐐
Amphion retweeted
I've added the MaskGCT TTS @gradio API to the Echo Mimic Space, so you can directly clone your voice before generating portrait generation 🤗
Try it —› huggingface.co/spaces/fffilo…
Fuck yeah! MaskGCT - New open SoTA Text to Speech model! 🔥
> Zero-shot voice cloning
> Emotional TTS
> Trained on 100K hours of data
> Long form synthesis
> Variable speed synthesis
> Bilingual - Chinese & English
> Available on Hugging Face
Fully non-autoregressive architecture:
> Stage 1: Predicts semantic tokens from text, using tokens extracted from a speech self-supervised learning (SSL) model
> Stage 2: Predicts acoustic tokens conditioned on the semantic tokens.
Synthesised: "Would you guys personally like to have a fake fireplace, an electric one, in your house? Or would you rather have a real fireplace? Let me know down below. Okay everybody, that's all for today's video and I hope you guys learned a bunch of furniture vocabulary!"
TTS scene keeps getting lit! 🐐
🔥🔥🔥MaskGCT is hot, making Amphion on the list of GitHub Trending again!
> SoTA TTS model
> Zero-shot cloning
> Emotional TTS
> Multilingual, now supporting English and Chinese
> Fully non-autoregressive and duration controllable
Try in HF and discord.gg/fRaQpH7s
GitHub: github.com/open-mmlab/Amphio…
MaskGCT: github.com/open-mmlab/Amphio…
Amphion retweeted
Fuck yeah! MaskGCT - New open SoTA Text to Speech model! 🔥
> Zero-shot voice cloning
> Emotional TTS
> Trained on 100K hours of data
> Long form synthesis
> Variable speed synthesis
> Bilingual - Chinese & English
> Available on Hugging Face
Fully non-autoregressive architecture:
> Stage 1: Predicts semantic tokens from text, using tokens extracted from a speech self-supervised learning (SSL) model
> Stage 2: Predicts acoustic tokens conditioned on the semantic tokens.
Synthesised: "Would you guys personally like to have a fake fireplace, an electric one, in your house? Or would you rather have a real fireplace? Let me know down below. Okay everybody, that's all for today's video and I hope you guys learned a bunch of furniture vocabulary!"
TTS scene keeps getting lit! 🐐
🚀🚀🚀 MaskGCT!
In addition to the HuggingFace demo: huggingface.co/spaces/amphio…
you can also join the discord space to play: discord.gg/fXmDZFur
Also pre-generated samples: maskgct.github.io/
@discord @discordbots @DiscordBotDevs @_akhaliq
🚀🚀🚀 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
It’s part of Amphion, finally published 🎉🎉🎉
🎤 New Research Breakthrough in Singing Voice Conversion! 🎤
Title: "SingVisio: Visual analytics of diffusion model for singing voice conversion"
Authors: @lmxue_ et al.
Check out the full paper here: doi.org/10.1016/j.cag.2024.1…
#ComputerGraphics #CagJournal #AI #MachineLearning #SVC
The Emilia dataset, 101k hours of multilingual in-the-wild speech data, is now available to download from HuggingFace! Join the discord if you have any feedback.
HF: huggingface.co/datasets/amph…
Discord: discord.com/invite/ZxxREr3Y
Amphion retweeted
📢📢Glad to share our latest survey on Foundation Models for Music! 🎶For both computer music researchers and ML researchers: this comprehensive review explores how LLMs and diffusion models are revolutionising music through music understanding, generation, therapy, and more.🎉🎉
🔥🔥We have open-sourced Emilia for speech generation, a 101k-hour dataset in six languages from in-the-wild (e.g. talk shows, interviews, debates). Checkout perf of model trained with it.
HF: huggingface.co/datasets/amph…
ArXiv: arxiv.org/abs/2407.05361
Demo: emilia-dataset.github.io/Emi…
SD-Eval benchmark dataset
Paper: arxiv.org/abs/2406.13340
GitHub: github.com/amphionspace/SD-E…
Amphion retweeted
💥Video generation is booming lately🤤!
🤩Try our🎙️𝐅𝐨𝐥𝐞𝐲𝐂𝐫𝐚𝐟𝐭𝐞𝐫 to add sound effects.
🌟HomePage: foleycrafter.github.io/
❤️Thanks to all the co-authors: Yicheng Gu @zengyh1900 @LeoXing8 Yuancheng Wang @drwuz @kaichen100
#FoleyCrafter #AudioGeneration #AISoundEffect