Comments (3)
Hi @c469591, we have no plans to directly port to the Windows/MacOS platform until now, since it will take much labor and testing cost. Besides, most models of Amphion are dependent on big data and large-scale training, so we think Linux may be a better choice, at least for now. If a Linux-based server is not available, we recommend to use huggingface space or colab to play Amphion.
However, we are planning to integrate some typical models into Colab/Jupyter Notebook, just for teaching and education. The specific date has not been decided. We hope to release them in this summer :)
from amphion.
hi,
I understand,
I've also tried rewriting .sh files on Windows, but it's more difficult than I imagined. However, I will continue to try.
Additionally, based on my own experience, Google Colab doesn't seem very user-friendly; it limits the runtime for each session and is not very stable. It's not a good option for me.
I'll give Hugging Face a shot, but currently, I'm still testing on AutoDL.
The downside of using GPUs on AutoDL is that it constantly costs money which is quite troubling for me.
And since my computer with an NVIDIA 3060 runs on Windows system—the virtual Linux subsystem in Windows isn't fully functional—it really gives me a headache.
from amphion.
Hi @c469591, thanks for your constructive feedback! We will review again and try our best to find a suitable third-party server in the future, when integrating our model for teaching and education.
from amphion.
Related Issues (20)
- [Feature]: Use ruff to improve code style HOT 1
- [BUG]: Uid format in `preprocessors/popbutfy.py` may be incorrect HOT 1
- [Feature]: Replace hand-craft hparams with dataclass and omegaconf framework HOT 1
- [Help]: something wrong with the run.sh on windows HOT 2
- [Help]: Performance Inferior to Demo Showcase in terms of "FACodec: Voice Conversion Samples" HOT 1
- [Help]: NaturalSpeech2 training and data preprocess issue HOT 4
- natural speech3 FACodec
- [Help]: Can use external pretrained codec for NeuralSpeech2
- [Help]: Reproduced TTA Results
- [Help]: Loss NaN occured while training VALL-E during the second stage (the NAR decoder) HOT 2
- [Help]: Number of total forward passes in the NaturalSpeech3
- [Help]: NS2 data preprocess problem
- [BUG]: could u pls help me with this? thanks! HOT 4
- [Help]: Want to ask about TTA task inference, why we need to add uncond_embeddings
- [Feature]: TTA - Can we set duration of output wav / Increase the length of wav output file
- [Docs]: need docs
- doesnt support python HOT 2
- nvm i wont use this
- Questions about Training, Models, and Plan for Chinese TTS HOT 2
- Doubt in CE-RVQ loss when training NaturalSpeech 2 HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from amphion.