Comments (7)
rafaelvalle
commented on May 18, 2024
1
We trained a new model that reduces the number of channels from 512 to 256 and still maintains the audio quality.
from waveglow.
yoyololicon
commented on May 18, 2024
Maybe the support of FP16 ?
from waveglow.
hdmjdp
commented on May 18, 2024
@rafaelvalle have your try to reduce the WN layers(n_layers) from 8 to 4?
from waveglow.
rafaelvalle
commented on May 18, 2024
No, we have not.
from waveglow.
TomGledhill
commented on May 18, 2024
Hello @rafaelvalle! Thank you all, for this awesome project!
Could you please share pretrained weights of model with reduced number of channels?
Thanks in advance!
from waveglow.
tugstugi
commented on May 18, 2024
@rafaelvalle I second @TomGledhill is it possible to share the model with 256 channels?
from waveglow.
rafaelvalle
commented on May 18, 2024
Here is the link for the model with 256 channels trained on LJS.
https://drive.google.com/open?id=1WsibBTsuRg_SF2Z6L6NFRTT-NjEy1oTx
from waveglow.
Related Issues (20)
- pose = list(self.allPose.keys())[list(self.allPose.values()).index(pose_ind)] ValueError: 'PD+00' is not in list
- GPU required or CPU compatible? HOT 1
- tts_waveglow_268m from_pretrained KeyError
- Waveglow Pretrained Model shall i use for male voice to do transfer learning? Need guidance
- I want to run a trained "yolov5s.pt" in a local pc for a usage of a opencv application .How can I do that in simples as a newbies to pytorch
- Is it possible to split denoiser module?
- Multispeaker trained model inferencing different voices HOT 1
- Can not load model HOT 1
- Converting audio samples to mel then back to audio just generates noise. HOT 3
- Convert log Mel bank energy to audio by your model
- Training different 'n_mel_channels' models HOT 2
- An important issue on multispeaker inference
- Continue Training from a checkpoint saved in checkpoints folder HOT 1
- spectrogram (image)-to-to wav
- how to make a list of the file names to use for training/testing? HOT 1
- why "audio = audio.astype('int16')" is uesd ? HOT 6
- Need help warm start model HOT 1
- ERROR: No matching distribution found for torch==1.0 HOT 2
- Can't install matplotlib
- WaveGlow: a Flow-based Generative Network for Speech Synthesis
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 waveglow.