Reuben Morais
400c9c0e5d
Streaming inference
2018-08-02 13:22:24 -03:00
Alexandre Lissy
646c9178cf
Non positionnal arguments. Everywhere.
...
Fixes #1443
2018-07-04 17:12:52 +02:00
Alexandre Lissy
914c923767
Augment tc download with branch
...
Fixes #1438
X-DeepSpeech: NOBUILD
2018-07-03 16:09:17 +02:00
Godeffroy
f1c433ab90
native_client/README.md - added hints about bazel and tensorflow versions, and some compile options
2018-04-18 15:33:17 +02:00
Alexandre Lissy
0a9bfbd41f
Switch to TensorFlow r1.6
2018-03-12 23:01:28 +01:00
Reuben Morais
4309cd5b6e
Update native client README to fix native model target name
2018-03-02 12:23:06 +00:00
Alexandre Lissy
ce80a094ba
Fix doc with no --config=monolithic for libctc_decoder_with_kenlm.so
...
Fixes #1260
X-DeepSpeech: NOBUILD
2018-02-20 11:10:26 +01:00
Alexandre Lissy
e4773028ba
Update doc for mmap-able model
...
Fixes #1248
2018-02-15 17:23:33 +01:00
Alexandre Lissy
bcfd4fd409
Update for r1.5
2018-02-14 11:58:48 +01:00
Alexandre Lissy
eac987a09c
Switch to reference TensorFlow r1.4 branch
2018-02-09 19:03:32 +01:00
Alexandre Lissy
ade66b015d
Build TensorFlow as monolithic into libdeepspeech.so
...
Also limit the set of included Ops to avoid wasting size.
2018-01-31 16:53:57 +01:00
Alexandre Lissy
b633048dff
Making v0.1.1 release
2018-01-31 13:18:41 +01:00
Alexandre Lissy
5b0ca1e410
Update to TensorFlow r1.4
...
Fixes #959
2017-11-30 18:51:13 +01:00
Alexandre Lissy
031addd5c8
Document deps
...
Fixes #1025
2017-11-27 15:42:46 +01:00
Reuben Morais
014d0c7273
Switch version number to 0.1.0
2017-11-24 12:09:34 -02:00
Reuben Morais
e8452b896f
Update docs to point to published Node packages
2017-11-23 16:01:14 -02:00
Alexandre Lissy
c95a1daab9
Switch to v0.0.3
2017-11-23 16:44:20 +01:00
Reuben Morais
5ba46cc2da
Revert "Update docs to point to npm packages"
2017-11-22 13:35:32 -02:00
Reuben Morais
570ba7db57
Address review comments
2017-11-22 13:25:55 -02:00
Reuben Morais
a84bbb40bf
Update docs to point to npm packages
2017-11-22 13:06:26 -02:00
Alexandre Lissy
4e6cad87a6
Add virtualenv documentation for Python
...
Fixes #983
2017-11-21 14:18:42 +01:00
Reuben Morais
5ce7a2d48f
Update README to include GIF and feature usage of the Python package more prominently
2017-11-17 20:15:22 +01:00
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
f1d89c02be
Lie about manylinux1 so we can get our packages on PyPI
2017-11-17 18:26:32 +01:00
Reuben Morais
9f1b20efc3
Rename util/tc.py to util/taskcluster.py
2017-11-08 14:34:05 -02:00
Alexandre Lissy
db09ab7d19
Preliminary support for libdeepspeech_model.so
2017-11-03 17:25:25 +01:00
Reuben Morais
9d8a060596
More review comments
2017-10-26 09:01:45 -02:00
Reuben Morais
06e2573880
Undo Node.JS makefile dependency change as it breaks automation
2017-10-26 09:01:15 -02:00
Reuben Morais
78f4380721
Address review comments
2017-10-25 17:09:10 -02:00
Reuben Morais
bbf9c76ab9
Update native client README to highlight prebuilt binaries and include Node.JS docs
2017-10-25 14:57:22 -02:00
Alexandre Lissy
66f9c4d481
Use libtensorflow_cc for C++ API
2017-06-28 20:57:12 +02:00
Chris Lord
91c682eac0
Use deepspeech Python library in util/audio.py
...
Deprecate duplicated code and use libdeepspeech for consistency and speed.
2017-06-27 10:16:54 +01:00
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
Chris Lord
910a664aa8
Separate libdeepspeech/c_speech_features/kissfft library builds
...
Build separate libraries for kissfft, c_speech_features and libdeepspeech.
This allows us to specify c99 for c_speech_features and should fix
issue #441 .
2017-03-22 13:30:55 +00:00
Chris Lord
2740336d08
Implement a native client using TensorFlow C API
2017-02-23 16:35:44 +00:00
