Malar Kannan
|
80c0ce403e
|
generating all words for a every voice first
|
2017-10-27 19:04:09 +05:30 |
|
Malar Kannan
|
cbf15ff662
|
type in fn name
|
2017-10-27 18:57:26 +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
|
82d0398d2c
|
formatted
|
2017-10-25 13:36:41 +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 |