Comments (4)
The 5 hours of default train/test data is taken from the Librispeech "dev clean". It is disjoint (no shared data points) with these other datasets in #6. So I would change the training set to be one of the big training sets, and use one of the following for the new validation:
- Just use the same, default validation.
- Use the "old", default training set as the new validation set (because it is a little bigger).
- Use both the "old" default training set as well as default validation set! You can combine them by simply having more than one data supplier. So in the
speech.yml
Kurfile, you currently have:
train:
data:
- speech_recognition:
<<: *data
url: "https://kur.deepgram.com/data/lsdc-train.tar.gz"
checksum: >-
fc414bccf4de3964f895eaa9d0e245ea28810a94be3079b55505cf0eb1644f94
# ...
validate: &validate
data:
- speech_recognition:
<<: *data
url: "https://kur.deepgram.com/data/lsdc-test.tar.gz"
checksum: >-
e1c8cf9cd57e8c1ae952b6e4e40dcb5c8e3932c81ecd52c090e4a05c8ebbea2b
And you can change it to something like this:
train:
data:
- speech_recognition:
<<: *data
url: "http://kur.deepgram.com/data/lsc100-100p-train.tar.gz"
checksum: >-
cad3d2aa735d50d4ddb051fd8455f2dd7625ba0bb1c7dd1528da171a10f4fe86
# ...
validate: &validate
data:
- speech_recognition:
<<: *data
url: "https://kur.deepgram.com/data/lsdc-test.tar.gz"
checksum: >-
e1c8cf9cd57e8c1ae952b6e4e40dcb5c8e3932c81ecd52c090e4a05c8ebbea2b
- speech_recognition:
<<: *data
url: "https://kur.deepgram.com/data/lsdc-train.tar.gz"
checksum: >-
fc414bccf4de3964f895eaa9d0e245ea28810a94be3079b55505cf0eb1644f94
Note that if you use multiple data suppliers, I would recommend using a bleeding-edge install of Kur. There were a couple of bugs we fixed up related to this since the last official release on PyPI.
from kur.
Yep, this is probably caused by not enough data, so like @liaoweiguo said, see issue #6 for alternative datasets that we provide.
from kur.
from kur.
Thanks a lot! I'll try with larger datasets. Should the validation set remain the same?
In #6 it is mentioned that train set is sampled from LibreSpeech train. Is it safe to assume that test is sampled from LibreSpeech test?
from kur.
Related Issues (20)
- Weights are not getting saved. HOT 2
- Validation loss diverging in speech example HOT 1
- add support for mxnet
- Truth Data generation Error HOT 5
- How to get text output from evaluate.pkl file ? HOT 1
- Running STT on specific file?
- AttributeError: module 'keras.backend' has no attribute 'set_image_dim_ordering' HOT 1
- RuntimeError: generator raised StopIteration HOT 6
- out of memory error
- How do I transcribe the wav file?
- Validation loss become higher after 20 hours training time HOT 3
- Weights for speech recognition are not restored when again starting the training as loss value climbs back to 1st epoch value i.e 316 instead of starting from reduced loss HOT 4
- Training for speech recognition using KUR on a distributed system. Is it possible? HOT 1
- CUDA_ERROR_NO_DEVICE HOT 1
- Import Voxforge to Kur HOT 1
- speech.yml prediction is empty HOT 2
- failed to find any available GPUs HOT 1
- The speed of training gradually decreases when using gpu HOT 4
- Training a dataset with non-latin characters HOT 1
- Error when training on custom data HOT 12
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 kur.