Comments (2)
I'll modify the main branch to add a feature to save the model through training (off by default).
from deepspeech.torch.
The latest commit added the above feature here. Hopefully this solves your issue (the model is always going to be large with this many params!).
from deepspeech.torch.
Related Issues (20)
- error when predict.lua
- CER calculation obviously wrong
- Librispeech training error HOT 2
- running pretrained net on CPU only HOT 2
- Getting wrong prediction results on pretrained librispeech model HOT 4
- Regarding the Language Model used HOT 7
- Error in CuDNN: CUDNN_STATUS_BAD_PARAM (cudnnGetConvolutionNdForwardOutputDim) HOT 4
- How to just evaluate a pre-trained network on an audio file? HOT 6
- Issue with Torch Dependencies HOT 6
- AN4 Setup problems HOT 4
- Realtime microphone prediction HOT 1
- Error running train.py using CUDA
- Totally wrong prediction during testing on pretrained model HOT 2
- No pretrained models params on main page + questions
- Unicode support HOT 6
- custom dataset formatting issue HOT 1
- Error Sample Rate 8khz HOT 7
- Out of memory issue when Train.lua HOT 1
- I get the same training error by every epoch HOT 2
- error when I test
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 deepspeech.torch.