Malar Kannan
|
307b4ce1c2
|
removed legacy similarity
|
2017-10-27 18:56:37 +05:30 |
|
Malar Kannan
|
938a9cf0a8
|
implemented tts gen variants
|
2017-10-27 18:53:22 +05:30 |
|
Malar Kannan
|
eb3ce8b7e5
|
wip high variant phoneme
|
2017-10-26 18:06:14 +05:30 |
|
Malar Kannan
|
e57576d6fa
|
discarding phoneme incapable synthesizers
|
2017-10-26 16:51:32 +05:30 |
|
Malar Kannan
|
a953fa3355
|
fixed progress
|
2017-10-26 16:18:17 +05:30 |
|
Malar Kannan
|
7a520b79f4
|
writing to csv proactively
|
2017-10-26 15:58:25 +05:30 |
|
Malar Kannan
|
05f36daf7e
|
refactored sample generation code
|
2017-10-26 15:27:22 +05:30 |
|
Malar Kannan
|
49e6a46efd
|
code cleanup
|
2017-10-26 12:48:31 +05:30 |
|
Malar Kannan
|
5824158af2
|
1. fixed neg values in spectrogram
2. refactored get word spectrogram code
|
2017-10-25 16:52:45 +05:30 |
|
Malar Kannan
|
f1e82a2539
|
added code to record and generate spectrogram, wip test model
|
2017-10-25 15:38:03 +05:30 |
|
Malar Kannan
|
a8f17ef764
|
refactored spectrogram and implemented record and generate spectrogram
|
2017-10-25 13:37:17 +05:30 |
|
Malar Kannan
|
82d0398d2c
|
formatted
|
2017-10-25 13:36:41 +05:30 |
|
Malar Kannan
|
e6f0c8b21b
|
1. clean-up code
2. implemented checkpoint model saving
|
2017-10-24 16:41:35 +05:30 |
|
Malar Kannan
|
77821093cb
|
Merge remote-tracking branch 'locnuc/master'
|
2017-10-24 11:55:57 +05:30 |
|
Malar Kannan
|
47991cb7ab
|
added audio recording snippet
|
2017-10-24 11:55:27 +05:30 |
|
Malar Kannan
|
71c49320c1
|
added changes
|
2017-10-24 11:55:04 +05:30 |
|
Malar Kannan
|
8be8fa2595
|
saving models and logs
|
2017-10-24 11:49:47 +05:30 |
|
Malar Kannan
|
03d49d83e7
|
updated learning rate
|
2017-10-23 20:21:44 +05:30 |
|
Malar Kannan
|
6f3bca61cf
|
1. fixed dimension issue in data
2. experimenting with different base network
|
2017-10-23 19:00:27 +05:30 |
|
Malar Kannan
|
e865f17a0d
|
pickling intermediate data to save memory usage
|
2017-10-20 12:52:11 +05:30 |
|
Malar Kannan
|
b3755ad80e
|
updated tested pickling
|
2017-10-17 19:17:44 +05:30 |
|
Malar Kannan
|
88edcdd239
|
seprated spectrogram generation code
|
2017-10-17 19:11:04 +05:30 |
|
Malar Kannan
|
51a6d6e804
|
added who data method
|
2017-10-17 19:04:07 +05:30 |
|
Malar Kannan
|
8ae5104201
|
added spectrogram to model data code and implemented simple rnn model
|
2017-10-17 18:56:42 +05:30 |
|
Malar Kannan
|
40c8675e4a
|
included keras - mnist siamese example
|
2017-10-13 17:59:53 +05:30 |
|
Malar Kannan
|
dccbec7cba
|
1. implemented spectrogram generator for audio files
2. imported siamese network class (wip)
3. added similarity measure based phoneme neighbor generator
4. fixed samplegen variants code
5. create triplets (wip)
6. updates
|
2017-10-13 16:40:57 +05:30 |
|
Malar Kannan
|
258356780f
|
created triplet code wip
|
2017-10-06 11:01:16 +05:30 |
|
Malar Kannan
|
7430d2dc9a
|
similarity wip
|
2017-10-05 17:37:49 +05:30 |
|
Malar Kannan
|
36722c1141
|
refactored
|
2017-10-05 16:54:41 +05:30 |
|
Malar Kannan
|
67f27ac683
|
1. included arpabet apple phoneme mapper
2. using only voices with phoneme capability and 3 rates only
|
2017-10-05 13:58:00 +05:30 |
|
Malar Kannan
|
0337f0d5be
|
1. using cli say instead of api since api generates empty responses sometimes
2. generating all words voices for each variants
|
2017-10-05 11:02:38 +05:30 |
|
Malar Kannan
|
9d700f18ca
|
implemented phoneme/voice/rate variant genration
|
2017-10-04 23:21:28 +05:30 |
|
Malar Kannan
|
d2c28fc63f
|
generated voice files using ios api
|
2017-10-04 17:51:39 +05:30 |