Comments (9)
@lucidrains Thank you very much for your reply!
Your efficiency is really high, you released a new version so quickly.
Regarding the implementation of the third point, I see that you use ResnetBlock, each ResnetBlock contains 2 convolutions and SiLU (it seems to be generally better than Relu), does this mean that each ResnetBlock is equal to 2 convolutions? I'm not very sure~ Maybe it really needs running experiments to determine the effect
from naturalspeech2-pytorch.
There is another small issue. When reproducing the NS2 paper, I used Torchinfo to count the parameter count. Each module follows the settings written in the paper (default configuration for those not written) and will never match.
For example, in the Phoneme Encoder, I changed the FeedForward in the code to the Convolutional FeedForward mentioned in the paper. When I set the Conv1D Filter Size of two 1D convolutions to 2048 and Kernel Size to 9, the parameter quantity is 119M. Only when one Kernel Size is 9 and the other Kernel Size is 1 can the difference be not much, which is 69M. It's not equivalent to 72M in the paper
Or Audio Codec, I initialized it as described in the paper
from audiolm_pytorch import SoundStream, EncodecWrapper
SoundStream(rq_num_quantizers=16,
codebook_size=1024,
codebook_dim=256,
strides=(2, 4, 5, 5))
the parameter quantity is 35M, only by modifying channels
and use_local_attn
can only be changed to the 27M mentioned in the paper. How did you solve the problem of mismatched parameter quantities? Or ignore it? Is it acceptable if the order of magnitude is correct?
Looking forward to your recovery very much!
from naturalspeech2-pytorch.
@JiaYK yup, just the general ballpark is ok
from my point of view, the field is an approximate science rather than delicate engineering. hit on a few main ideas and it should be fine
from naturalspeech2-pytorch.
@JiaYK hey yes, i am aware of 1 and will get that done today!
for 2, RMSNorm
has been used successfully in a number of large language models by now (alphacode, llama). I think we can safely start using it
for 3, i was actually not sure about that, but will be adding residuals (it will be redone as resnet blocks)
from naturalspeech2-pytorch.
@JiaYK ok, 1 should be done, will probably get 3 done today too
from naturalspeech2-pytorch.
@JiaYK ok, 3 should be done too! let me know what you think
from naturalspeech2-pytorch.
@JiaYK oh true, yea, let's make that a hyperparameter
from naturalspeech2-pytorch.
@JiaYK although i guess it is still sensitive to certain decision in the neural network. not very apt description
let's just say... very different than traditional engineering
from naturalspeech2-pytorch.
Thank you very much for your reply~ Then I will not worry about the specific parameters, and give priority to realizing all the functions!
from naturalspeech2-pytorch.
Related Issues (20)
- Discuss details regarding loss function HOT 9
- Torch, CUDA version
- example model HOT 2
- The package fails to reference naturalspeech2_pytorch.utils.* HOT 4
- Question about generate speech HOT 5
- Trainer support for audio file, prompt pairs HOT 2
- ValueError: common is not allowed HOT 1
- WaveNet HOT 3
- Generate speech from Text HOT 1
- How to generate song with my voice? HOT 1
- Is KL-Divergence loss missing in Aligner loss definition? HOT 7
- unconditional version seems not to work correctly HOT 5
- Conditional DDIM sampling speed
- Will this work continue?
- Could you provide the pretrained model?
- Duration pitch loss not used. HOT 2
- Model study questions
- Inference code questions
- @wonwooo
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 naturalspeech2-pytorch.