Alexandre Lissy
3c7bfec840
Remove scipy 0.19.1 hard-requirement
2017-12-04 11:23:02 +01:00
Reuben Morais
014d0c7273
Switch version number to 0.1.0
2017-11-24 12:09:34 -02:00
Alexandre Lissy
c95a1daab9
Switch to v0.0.3
2017-11-23 16:44:20 +01:00
Alexandre Lissy
a26e0d8fa4
Ensure _model.so and _utils.so are inside DeepSpeech package
...
Fixes #1001
2017-11-22 16:12:01 +01:00
Reuben Morais
d12201cef4
Update metadata for Python and Node.JS packages
2017-11-21 10:43:44 -02:00
Reuben Morais
937c304682
Bundle the Python client as an entry point script
2017-11-17 18:26:32 +01:00
Reuben Morais
52d9a8b265
Bump version to 0.0.2 to workaround PyPI limitations
2017-11-17 18:26:32 +01:00
Reuben Morais
92e53a7a06
Add -gpu prefix to CUDA enabled packages
2017-11-17 18:26:32 +01:00
Alexandre Lissy
08f01c1727
Bundle libs into Python/NodeJS bindings packages
...
Fixes #908
2017-11-03 16:22:48 +01:00
Alexandre Lissy
20e0138900
Prebuilt ARM Python & NodeJS bindings
...
Fixes #915
2017-10-31 15:43:49 +01:00
Alexandre Lissy
abec2ec512
Remove scipy dependency from Python bindings
...
Fixes #919
2017-10-30 19:23:03 +01:00
Alexandre Lissy
910964d694
Stick to scipy 0.19.1
...
Fixes #905
2017-10-25 16:32:08 +02:00
Alexandre Lissy
42075082be
Cleanup makefile
...
Fixes #874
2017-10-06 11:35:53 +02:00
Alexandre Lissy
1f45a6b168
Add scipy and numpy deps to deepspeech python bindings
...
Fixes #744
2017-07-26 11:01:23 +02:00
Alexandre Lissy
331a7f291c
Change library link ordering for python binding
...
This fixes issue #578
2017-06-30 08:48:25 +02:00
Alexandre Lissy
66f9c4d481
Use libtensorflow_cc for C++ API
2017-06-28 20:57:12 +02:00
Chris Lord
d829eb4436
Split audioToInputVector into a separate library
...
Split out functions that don't depend on TensorFlow into a separate
library to avoid opening the TensorFlow library if it's not necessary.
2017-06-27 10:16:54 +01:00
Chris Lord
08deda2b92
Improve build process and instructions to fix performance issues
...
Certain optimisations that TensorFlow recommends cause significant
performance penalties in c_speech_features. Explicitly disable these
features in the BUILD file only for c_speech_features.
The build has been restructured to produce a single deepspeech library,
rather than 3 separate deepspeech, c_speech_features and kissfft
libaries. This should make the deepspeech client and libraries
significantly easier to use and distribute.
2017-05-17 10:52:14 +01:00
Chris Lord
10068fc40e
Add libdeepspeech python bindings
2017-05-02 10:41:59 +01:00
