Comments (8)
The models are quite large. It takes time to fully download them to RAM, simply. You can monitor the process via python -v, of via resource monitor, the default GUI ones in Windows etc will do.
from tts.
But the delay is present regardless of whether I'm synthesising speech. Even if I'm simply doing tts -h the delay is the same length of time. I can see using my resource manager that the resources are only allocated after this delay period, and are allocated almost instantaneously.
from tts.
Also the memory hard faults may be to blame, especially on e.g. Droids.
I wrote a snippet to monitor just that:
pidstat_while() {
echo
pidstat -r | awk 'NR<=3 {print $0}'
echo
while true; do
pidstat -r | awk 'NR>3 {print $0}' | sort -k8nr -k5nr | head -n 1
sleep 2
done
}
It is a function that you can run by typing pidstat_while
after pasting the above.
It even runs in Termux, but in prooted Debian.
In very short, it shows you the most memory intensive process, and the hard faults. If you have too many (say, over 50 per seconds) - the model is being memory mapped (aka loaded) from disk, now and then. (Excuse my maybe naive and non-IT explanation of the root cause... )
from tts.
I'm away from my PC for the next week, I'll run this and see what it says once I have access to it again, thanks!
from tts.
I didn't really understand what you were talking about and asked a friend, they said because I'm on Windows I won't be able to run what you've sent
from tts.
First of all, you're using a very outdated TTS version (you need at least Python 3.9 to get the latest). Then, making separate CLI calls will always be slow because you have to load the model every time, so e.g. use the server: https://docs.coqui.ai/en/latest/inference.html#on-the-demo-server-tts-server
from tts.
Ah okay, thanks! I had no idea I was outdated, I tried installing on Python 3. something greater than 8 and it told me I needed Python 8. I'm going to assume there must have been some user error there, once I'm able I'll try a fresh reinstall and look into creating the server.
from tts.
Yep, the server runs faaar faster! Thanks, the first line of the server part of the wiki tells you to not use it in real-time applications so I avoided looking into it further, there was my mistake! Maybe this could be made clearer? Thanks!
from tts.
Related Issues (20)
- Realtime voice conversion support
- [Bug] VITS gpu utilization
- [Bug] ModuleNotFoundError: No module named 'TTS' (From inside the TTS folder) HOT 1
- [Feature request] Run in the browser?
- Can't start training due to recursion depth error
- Can't install TTL on Windows 11: Could not build wheels for TTS HOT 4
- [Feature request] Allow the use of `logging` instead of `print` HOT 3
- [Feature request] GPU Mac Silicon Chip HOT 1
- [Bug] Error during installation on Mac HOT 1
- [Bug] YourTTS alignment is weird
- [Bug] XTTS Finetuning - xtts_demo.py - Collab HOT 1
- [Feature request] Website Improvements
- [Train XTTSv2 hifigan decoder] Provide script
- [Bug] xtts_v2, AttributeError: 'TTS' object has no attribute 'speakers' HOT 3
- Hello, Please add bengali language cloning [Feature request]
- UnboundLocalError: local variable 'dataset' referenced before assignment [Bug] HOT 3
- [Bug] Anyway to run this as docker-compose ? HOT 2
- [Bug] DDP not actually working HOT 1
- [Bug] 'tts_models/ben/fairseq/vits' model didn't found Character 'য়' not found in the vocabulary.
- [Bug] Anyway to run this as docker-compose ? HOT 2
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 tts.