Comments (1)
There are three main tensors created by the data loader:
-
src_tokens
: the tokens for the source sentence -
target
: the tokens for the target sentence -
input_tokens
: the output token produced by the decoder at$t-1$ . During training this is the same astarget
but shifted by one time step (e.g., iftarget = 3 4 5 6
theninput_tokens = 0 3 4 5
. During inference this is the actual token generated in the previous time step.
from fairseq.
Related Issues (20)
- FileNotFoundError: [Errno 2] No such file or directory: '/fsx/data/VoxLingua107/manifest/dict.label.txt'
- DEPRECATION: omegaconf 2.0.6 has a non-standard dependency specifier PyYAML>=5.1.*. pip 24.0 will enforce
- Why the nllb 3.3B will still occupy 5.7GB memory while the model has loaded to GPU and occupied 13.17GB GPU-memory?
- the new LID Model lid218e.bin doesn't detect Chinese/Japanese correctly.
- nllb 3.3B translate from Chinese to Japanese got: () () () () () () () () () () () () ()
- nllb 3.3B translate from Chinese to Korean got: , , , , , , , , , , , , , , ,
- Fairseq inference with Tauri frontend
- Wrong results when running inference with pytorch and MPS backend HOT 1
- issue numpy when try to TTS method
- Roberta base for Custom named-entity recognization
- raise FileNotFoundError("Dict not found: {}".format(args.data))
- Any plan to support TTS for cmn?
- AssertionError: Sentences lengths should not exceed max_tokens=400000 HOT 1
- Installation Error: M1 Mac HOT 1
- Importing `hydra.experimental` results with an ImportError
- MMS 下载预训练模型MMS-1B:L1107,想测试一下安多藏语
- assert step < max_len, f"{step} < {max_len}" AssertionError: 60 < 60
- [Hubert] Use different kmeans models for train and valid dataset?
- ModuleNotFoundError: No module named 'fairseq.criterions.' HOT 2
- FileNot Found error
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 fairseq.