Comments (5)
Rather than use latgen-faster, you may use decode-faster to get the 1-best hypothesis directly. This should speed up decoding. Refer to https://github.com/srvk/eesen/blob/master/asr_egs/wsj/steps/decode_ctc.sh
Also, reducing beam and max_active can also speed up decoding. But caution that this might hurt recognition accuracy.
from eesen.
What is the real time factor for your decoding?
from eesen.
Can I ask what do yo mean by "real time factor"?
Best
from eesen.
What is the length of the speech utterance you are trying to decode? How long does decoding take exactly?
from eesen.
Hi Yajie
My utterance will up to 22 words length, for sentence like this, some are recorded in very noisy environment. I notice that for such utterance, it is more likely to use more than 10 seconds in the latgen-faster part.
For sentence with similar length which recorded in a quieter place, it might only take 2-3 seconds.
But, for sentence of such length, is it realistic to expect better speed then 2-3 seconds?
Best
from eesen.
Related Issues (20)
- Clean up v2 for swb
- DeepBiLSTM HOT 2
- Missing label.counts HOT 3
- Query on LibriSpeech Character Error Rate HOT 2
- difference in output labels HOT 1
- Memory Leak HOT 1
- failed: Dim() == v.Dim() HOT 2
- Potential overflow when calculating exp
- Clarification Regarding Using WFST decoding HOT 1
- Installing error HOT 8
- Training Error when run tedlium recipe HOT 2
- LatticeFasterDecoder failed with "link_extra_cost == link_extra_cost" HOT 1
- Cannot install openfst-1.4.1 HOT 2
- Read failure in ReadBasicType, file position is -1, next char is -1
- KALDI_ASSERT: at train-ctc-parallel:AddMatMat:cuda-matrix.cc:570, failed: m == NumCols()
- Why do we need space and unk symbols in the char mode for acoustic model? HOT 6
- Why do we need to compile the tokens to FST in wsj recipe?
- Can not run training program with cuda 10.2 HOT 3
- Librispeech - Training starting error HOT 3
- Determinizability of TLG.fst in the phonetic case
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 eesen.