06d9669e79
Add sampled training support
2018-07-11 12:45:41 -05:00
1f5e17ba0a
Formatting
2018-07-11 12:45:41 -05:00
afbace91b1
Add logs to .gitignore
2018-07-11 12:45:41 -05:00
6a8b7b8ea8
Add delta vector support
2018-07-11 12:45:41 -05:00
ebd5e09feb
Rework train script to use new Trainer class
...
This allows IncrementalTrainer to share similar behavior
2018-07-11 12:45:41 -05:00
4da65d1f37
Quiet tensorflow when performing predictions
2018-07-11 12:45:41 -05:00
a946de21ce
Make ListenerParams proper class via attr
2018-07-11 12:45:41 -05:00
779ddd2d02
Use vectorize_raw instead of rewriting mfcc call
2018-07-11 12:45:41 -05:00
0da11b33bd
Make mfcc generation use mfcc_size instead of feature_size
...
feature_size could be different.
2018-07-11 12:45:41 -05:00
603385291f
Fix up docstring for create_model
2018-07-11 12:45:41 -05:00
252abbeb15
Make loss bias use module level variable
2018-07-11 12:45:41 -05:00
3fc1fe4789
Add libatlas-base-dev to debian dependencies
...
It is a runtime dependency of the piwheels tensorflow whl
2018-07-02 20:41:54 +00:00
1f15f9da92
Increase default batch size in train-incremental
2018-06-25 12:37:56 -05:00
a83769302f
Remove dist/ folder from tar
2018-06-22 10:38:34 -05:00
c663719cce
Increment version to 0.2.0
2018-06-20 16:49:50 -05:00
523eb719f1
listen: not-wake-up: increase the random value's range
...
the old range is too narrow and therefore make data override often happen.
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
2018-06-20 16:49:50 -05:00
83bd6804c9
README: replace precise-record with precise-listen
...
sync with commit 19bf49a4a
2018-06-20 16:49:50 -05:00
3add0c320e
activate: add a running directory independent noitfier
...
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
2018-06-20 16:49:50 -05:00
7d28057ffd
Add build.sh for building properly named packages
2018-06-20 16:49:50 -05:00
3e507b16c4
Support Python 3.4 on a pi 3
2018-06-20 15:11:57 -05:00
d0e3207639
Increment runner version to 0.2.1
2018-06-18 16:17:00 -05:00
bdd8a8e204
Fix setup.sh
...
Fix missing semicolon and only use brew on mac
No need to install packages in linuxbrew
2018-06-14 16:45:57 -05:00
19f95ae034
Use piwheels for tensorflow on a raspberry pi and upgrade to tensorflow 1.8.0
...
Way less of a hassle
2018-06-14 16:34:13 -05:00
b14c4b34b8
activate: use a right audio player for mac osx
...
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
2018-06-13 14:33:58 -05:00
031a72061e
Make pip installation more modular
...
Allows creating your own venv
2018-06-13 13:41:48 -05:00
8a03eef9ca
Refine .gitignores
2018-06-12 13:58:41 -05:00
e3e15f65e7
Don't output params warning when it doesn't make sense
2018-06-12 13:58:31 -05:00
d6284832ce
Add brew dependencies to fix mac install
2018-06-04 15:09:34 -05:00
009e9c1ef9
Add swig and libpulse-dev as dependencies
...
This fixes #8
2018-05-30 12:19:35 -05:00
989e29bb83
Support pb files in precise-test
2018-04-26 19:04:05 -05:00
ef96763327
Make indentation consistent in bash scripts
2018-04-20 12:09:53 -05:00
ffcf4a0e9d
Support installing tensorflow on other Python versions when on a pi
2018-04-20 12:06:10 -05:00
b74e80568b
Fix bug with reading from non-pyaudio stream
...
pyaudio's stream.read is in samples whereas most other streams read in bytes
2018-04-19 13:50:50 -05:00
09767fa675
Ensure speechpy is updates
2018-04-18 23:48:22 -05:00
0cbb98fa78
Increase default weight of weighted_log_loss to 0.7
...
No point in using it by default if it isn't weighted. This makes it reduce false positives by default
2018-04-18 23:11:54 -05:00
bc7c73a4a9
Add link long_description field pointing to the GitHub README
2018-04-18 23:10:54 -05:00
09c728fb33
Fix locking on PreciseRunner.stop()
...
This fix only applies to when stream is a ReadWriteStream
2018-04-18 22:24:54 -05:00
a3274b8d33
Fix major bug in precise-train-incremental
...
Previously it wouldn't update its own buffer so the files it would save would be mostly silence
2018-04-18 17:52:09 -05:00
755af134f6
Use K.mean instead of K.sum in loss
...
This makes the loss actually reasonable rather than something like 132.3
2018-04-18 17:26:14 -05:00
bee65e6c8b
Upgrade requirements and update speechpy
...
This brings in significant speed improvements to mfcc calculations
2018-04-18 16:20:13 -05:00
476728b138
Add warning if loading from folder with many wavs without specifying tags file
2018-04-18 16:09:46 -05:00
45c72a80c2
Add rename folder and tags arguments
...
Everything is now referred to as tags rather than db since it's a set of tags not a database. It also switches the positional argument to refer to the regular structured data folder, with a separate tags-folder option to override where to load the file ids from the tags from
2018-04-18 15:59:02 -05:00
19bf49a4ae
Rename precise-record to precise-listen
...
This just makes a lot more sense. It's not recording you; it's listening to you
2018-04-18 14:48:43 -05:00
c1ae0a7bd2
Fix long cooldown threshold
...
Now, it is much shorter by default, gets reset every subsequent activation, and varies correctly with chunk size
2018-04-18 00:03:13 -05:00
bb4cb4badd
Fix double slash when loading from folder ending in slash
2018-04-17 20:04:02 -05:00
cb00e03d2d
Fix chunk size parameter in precise-record
2018-04-17 18:33:08 -05:00
9418990ff1
Don't train when activation subsides in incremental training
...
This allows batching up larger amounts of data before retraining
2018-04-16 17:31:53 -05:00
607db0437f
Remove extra files
...
These files were accidentally committed
2018-04-16 16:27:06 -05:00
bd7961d240
Change speechpy to local fork
...
This includes a performance improvement in mfcc calculation
2018-04-16 16:24:49 -05:00
c94a0a17d5
Increment runner version to 0.2.0
2018-04-13 01:09:22 -05:00
Matthew Scholefield
Wu Zhangjin