Comments (3)
I can take it but first I need to add fix for limiters
from dl-art-school.
Where can I change the path to save the model? I'm training on Colab and I want it to save on Google Drive because when the environment disconnects, I lose all the checkpoints
Previously, I didn't want to symlink the experiments folder with gdrive storage because of how big each checkpoint was, relative to 15GB of free storage
Now that the default mechanism is to autodelete old checkpoints && also to not save unimportant stuff like training states / EMA, i think this is a lot more feasible
from dl-art-school.
Where can I change the path to save the model? I'm training on Colab and I want it to save on Google Drive because when the environment disconnects, I lose all the checkpoints
Previously, I didn't want to symlink the experiments folder with gdrive storage because of how big each checkpoint was, relative to 15GB of free storage
Now that the default mechanism is to autodelete old checkpoints && also to not save unimportant stuff like training states / EMA, i think this is a lot more feasible
DL-Art-School/codes/utils/options.py
Lines 35 to 61 in 43f445d
I think we need to make changes to this file so that it can be edited through the configuration file.
from dl-art-school.
Related Issues (20)
- Separating
- The process cannot access the file because it is being used by another process HOT 1
- Please help RecursionError: maximum recursion depth exceeded while calling a Python object HOT 1
- Got error trying to test the fine-tuned model HOT 1
- Error no kernel image is available for execution on the device HOT 2
- Very detailed tutorial up-to-date HOT 2
- finetune on single speaker HOT 1
- Anyone tried Multi-lingual Tortoise?
- Unexpected keys in state dict when loading Unified Voice HOT 6
- Multi-gpu option is possible? HOT 2
- getting this error:RuntimeError: CUDA error: invalid device ordinal
- I need help with google colab HOT 3
- how to resolve this when i train the japanese voices HOT 4
- Error on ljspeech train starting in google colab: Unexpected key(s) in state_dict: "gpt.h.0.attn.bias", ... HOT 2
- Only using half the capacity of my vidoe card RTX 4090? (12 out of 24G)
- When do I stop the training? How do I know I should stop (Image inside)
- Is this the only voice cloning tech available right now? HOT 2
- Control the length of AUDIOs generated????
- Ghoost voices at the end of sentence in audio generation.
- Multi-GPU usage
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 dl-art-school.