coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
748 Commits
80 Branches
98 Tags
316 MiB
Commit Graph

748 Commits (7b2804cc0d02f2ffa9012ae6271f81205fc2d55c)

Author SHA1 Message Date
Eren Golge 5a91db56cc remove aux file 2019-02-20 17:15:03 +01:00
Eren Golge 2eaa1fec5a Merge branch 'master' of github.com:mozilla/TTS 2019-02-20 17:14:35 +01:00
Eren Golge 8100360c71 bug fix for initialization of the model 2019-02-20 17:14:08 +01:00
Eren Golge b571095186
Update README.md 2019-02-20 16:54:04 +01:00
Eren Golge 71f1f0c4c0 partial initialization fix 2019-02-20 16:46:10 +01:00
Eren Golge 9fecbb7bcc setup.py update 2019-02-20 16:45:50 +01:00
Eren Golge 6e86d0d0c4 .compute update 2019-02-20 16:45:31 +01:00
Eren Golge e825944100 README update 2019-02-18 13:53:47 +01:00
Eren Golge f6c4c101ff Merge branch 'master' of github.com:mozilla/TTS 2019-02-18 13:52:35 +01:00
Eren Golge e2052f9f06 README update 2019-02-18 13:51:57 +01:00
Eren Golge cc88284c8a README update 2019-02-18 13:49:14 +01:00
Eren Golge db7f3d36e7 README updates 2019-02-18 13:42:33 +01:00
Eren Golge e2d9b0e27c Merge branch 'dev' 2019-02-18 13:08:47 +01:00
Eren Golge 81b40f00e7 Update Benchmark notebook 2019-02-18 13:07:28 +01:00
Eren Golge 1c99be2ffd Change window size for attention 2019-02-18 13:06:26 +01:00
Eren Golge 97a16cedbf phoneme punctuation bug fix 2019-02-16 03:20:04 +01:00
Eren Golge 4d2c374cfd Filter out shape mismatch laeyrs in restoriong model for finetunning 2019-02-16 03:19:26 +01:00
Eren Golge 6ea31e47df Constant queue size for autoregression window 2019-02-16 03:18:49 +01:00
Eren Golge 11b6080cfd config update for r=2 2019-02-16 03:17:59 +01:00
Eren Golge bc615339d5
Update README.md 2019-02-12 16:10:22 +01:00
Eren Golge 55605c9b58
banner added 2019-02-12 15:59:10 +01:00
Eren Golge 90f0cd640b memoru queueing 2019-02-12 15:27:42 +01:00
Eren Golge ebc166b54f Merge branch 'dev-embedding-init' into dev 2019-02-12 10:14:14 +01:00
Eren Golge ca5b7d6c69 set learning rate for restored model 2019-02-12 10:05:19 +01:00
Eren Golge 4fad1971cd set learning rate for restored model 2019-02-12 10:04:39 +01:00
Eren Golge d03865ed05 configurable loss weigting for lower frequencies 2019-02-12 10:04:18 +01:00
Eren Golge 0ab59263ca config.json changes for ljspeech 2019-02-12 10:03:55 +01:00
Eren Golge c5b6227848 init with embedding lyaers 2019-02-06 16:54:33 +01:00
Eren Golge d28bbe09fb Attention bias setting Revert to old 2019-02-06 16:23:01 +01:00
Eren Golge eb839a7acd small buggy fix for phoeneme sequencer 2019-02-05 11:57:12 +01:00
Eren Golge 0308c92c16 pick best model by loss function is run_eval is true 2019-02-05 11:56:44 +01:00
Eren Golge e12bbc2a5c init decoder states with a function 2019-01-22 18:25:55 +01:00
Eren Golge 66f8d0e260 Attention biased chaged 2019-01-22 18:18:21 +01:00
Eren Golge 83d6f1dcee README update 2019-01-21 15:05:16 +01:00
Eren Golge b011dafbab pass num_chars in train.py 2019-01-21 14:52:40 +01:00
Eren Golge 328db7757d one more phoneme char for en-uk 2019-01-18 13:35:51 +01:00
Eren Golge 4749bc211e Add new char to phoneme symbols for en-gb 2019-01-17 15:48:37 +01:00
Eren Golge 562d73d3d1 Soem bug fixes 2019-01-17 15:48:22 +01:00
Eren Golge 4431e04b48 use sigmoid for attention 2019-01-16 16:26:05 +01:00
Eren Golge 7e020d4084 Bug fixes 2019-01-16 16:23:04 +01:00
Eren Golge af22bed149 set bias 2019-01-16 15:53:24 +01:00
Eren Golge 915783e10e enable phoneme based synthesizing 2019-01-16 15:53:07 +01:00
Eren Golge 72341ae22a phoneme usage bug fix 2019-01-16 13:09:47 +01:00
Eren Golge b241104778 Make phoneme training configurable through config.json 2019-01-16 13:07:03 +01:00
Eren Golge 8d87791470 Remove TWEB 2019-01-16 12:33:24 +01:00
Eren Golge b78fc96115 Change embedding layer init to old version 2019-01-16 12:33:24 +01:00
Eren Golge 5733eab90b Add configurable phoneme cache path 2019-01-16 12:33:24 +01:00
Eren Golge 7af1aeaf7a Add M-AI-labs preprocessor and set config for en_UK 2019-01-16 12:33:24 +01:00
Eren Golge f4fa155cd3 Make attn windowing optional 2019-01-16 12:33:07 +01:00
Eren Golge 8969d59902 Use the last attention value as a threshold to stop decoding. since stoptoken prediction is not precies enough to synthsis at the right time. 2019-01-16 12:32:40 +01:00