Comments (2)
Such kind of generation requires some techniques like an "island-driven search", which is not a quick hack. Can someone implement it? or is there any reference for the code like that?
from julius.
After experimenting with this for a while, I found that using a fast script engine such as Julia it was quite feasible to generate long lists of candidate prompts and apply a filter to extract what was required.
One detail which might be interesting is that given a word, what is the probability that any prompt will contain that word in the generate
process? Say you desire ten different prompts containing the word - knowledge of the probability would enable you to generate the required raw list and then apply the filter. Without the prob, user has to guess an overly large number, apply the filter and then randomly sample from the output - there is a good chance that the list will be longer than required.
from julius.
Related Issues (20)
- outpute file .out problem
- How to run ../julius/julius/julius -C julius.jconf -dnnconf dnn.jconf command
- Is there a tutorial to go with this app?
- Is the creation of DNN models with HTK + inference with julius still a good choice HOT 2
- About training
- having issues installing julius on a macbook with M1 chip
- Juliusを実行しようとするとエラーで動きません
- Deleted
- Possible data race issues HOT 1
- Suggestions to avoid communication deadlocks HOT 1
- too many arguments in call to 'connect_to_output_device'
- how to know the absolute start and end timestamps of each sentence
- Failed to recognize Audio
- mkgshmm does not install HOT 1
- Makefiles do not honour DESTDIR setting
- Julius does not run
- m_jconf error in the linux terminal HOT 1
- Why can't I use DNN and grammar together? HOT 2
- may be out of bounds
- breathing sounds when using a grammar model for speech recognition
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 julius.