Comments (3)
Hi there,
First, I want to remind that GOPTNoPhn
is way worse than GOPT
, and should only be used for analysis purpose.
Second, in this script, we hardcoded the sequence length as 50, that's why the positional embedding has shape [1,55,41] (50 + 5 CLS tokens = 55). You should either 1) change your input sequence length to 50, something like below:
# embed_dim is the width of the transformer, we suggest to set it as feat_dim, 41 is a quite weird value to me
a = GOPT(embed_dim=41, num_heads=4, depth=2)
# [batch_size, seq_len, feat_dim]
data = torch.randn(2, 50, 84)
# [batch_size, seq_len]
phn = torch.randint(40, (2, 50))
a(data, phn)
or 2) modify the GOPT model sequence length to be your sequence length + 5 (i.e., in your example, if your sequence length is 4, than you should set positional embedding length of 4+5=9).
Line 145 in 5ec31ca
Hope this help.
-Yuan
from gopt.
Also, if you do have access to Google Colab, I'd suggest starting from our colab example at https://colab.research.google.com/github/YuanGongND/gopt/blob/master/colab/GOPT_GPU.ipynb
from gopt.
Ok, I got it! thanks for your help, now I can run it.
from gopt.
Related Issues (20)
- step 3 in inference your own data confusion HOT 2
- while running run.sh in gop_speechocean it get error in visualize_feat.py AttributeError: 'tuple' object has no attribute 'shape' HOT 4
- The result seems to be no change HOT 19
- Сomparison with other works
- Can I assess random .wav without corresponding script?
- Can't not infer my own data, the result belongs to speechocean762 dataset
- The result of u1,u2,u3,u4,u5 is always higher than 1.5 HOT 2
- About infer the data HOT 2
- 测试自己的数据时,均值和方差怎么算出来的 HOT 3
- Hi, I want to add some words to text-phone from CMU dict and librispeech-lexicon, but they are different with speechocen762 HOT 2
- my own data length limit HOT 4
- the number of my own data HOT 1
- Interpreting the result HOT 7
- I could not find "load_human_scores" and "load_phone_symbol_table" from utils. HOT 1
- What is the point of cleaning lexicon in the dictionary: librispeech-lexicon.txt HOT 2
- Is it possible to apply GOPT in real life application? HOT 5
- how to infer or predict my own trained model HOT 4
- How to improve speed for GOPT HOT 1
- Can not reproduced similar result using pretrained model checkpoint and released data. HOT 1
- run the code on cpu HOT 1
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 gopt.