Comments (2)
After searching, I found the basis for you to do so, here is a relevant quote
Shi B, Hsu W N, Lakhotia K, et al. Learning audio-visual speech representation by masked multimodal cluster prediction[J]. arXiv preprint arXiv:2201.02184, 2022.
from deep_avsr.
Yes, the training is similar to joint training. I hadn't referred any papers for it nor it was supposed to be a formal joint training procedure. I wanted the end AV network to be usable with all the three cases (AO, VO, AV). So to avoid the network getting overtuned for only the AV case, I added some AO/VO training samples in between (governed by AO/VO probabilities) to kind of regularize the network. The end output values were as per expectations so I didn't dig in further to improve the joint training process.
from deep_avsr.
Related Issues (20)
- Transformer Decoder in jointDecoder in avnet HOT 1
- Transferring to train set was not going well HOT 9
- ctc_loss problem when running on multiple GPUs HOT 3
- Details of visual fronted model HOT 2
- Language Model Execution Never Ends HOT 8
- Question about the implement HOT 1
- The Validation WER in pretrain is always 1.0 HOT 5
- When pretrain VO model, loss reduce a few epochs, but immediately increase and remain. HOT 3
- What does <EOS> and " " mean? HOT 1
- CUDA out of memory on preprocess.py HOT 1
- The python version 3.6.9 is not supported anymore. HOT 2
- Where is the seq2seq model at 'audi_visual' or 'video only'? HOT 1
- Questions about meanings of variable in beam search
- preprocess error HOT 2
- Error happening when evaluating HOT 1
- RuntimeError: cublas runtime error HOT 2
- About loss curve HOT 4
- How AO and VO model are trained? HOT 1
- audio-visual.pt file HOT 4
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 deep_avsr.