Commit Graph

108 Commits (b22c7d4a29eb4b9b9cd26a4f2058d81979b92c37)

Author SHA1 Message Date
Thomas Werkmeister 215eb014ca enforce list append semantic; prevents numpy add 2019-07-26 13:40:58 +02:00
Thomas Werkmeister 468abc0872 Merge branch 'dev' of github.com:mozilla/TTS into patch-6 2019-07-24 11:26:54 +02:00
Thomas Werkmeister d4045fd47b unused var 2019-07-23 14:30:06 +02:00
Thomas Werkmeister 4c9fbeeaf8 simplified folder variable 2019-07-23 14:23:36 +02:00
Thomas Werkmeister 78c3897599
root path speaker matching
added data root path in speaker matching for mailabs, this way you don't need to start at the very bottom of the folder hierarchy if you want to explicitly define metafiles.
2019-07-23 09:47:52 +02:00
Eren Gölge ea8f295538
Merge pull request #238 from twerkmeister/dev
fixed usage of bos&eos char with caching
2019-07-22 15:13:37 +02:00
Thomas Werkmeister 116a21b659
lint indentation 2019-07-19 16:26:36 +02:00
Thomas Werkmeister c613f8e664
Not using mix folder for mailabs data 2019-07-19 16:23:12 +02:00
Thomas Werkmeister f59543d127 fixed usage of bos&eos char with caching 2019-07-19 15:17:35 +02:00
Reuben Morais 057a50a889 Merge branch 'dev' into contribution-grease 2019-07-19 11:41:14 +02:00
Eren Golge 4336e1d338 fix unittests for the latest updates 2019-07-19 11:12:48 +02:00
Reuben Morais 11e7895329 Fix Pylint issues 2019-07-19 09:08:51 +02:00
Thomas Werkmeister 7be11457e7
default argument mailabs 2019-07-17 16:04:17 +02:00
Eren Golge fd081c49b7 split dataset outside preprocessor 2019-07-16 21:15:04 +02:00
Eren Golge 59a0606e06 provide meta data list externally 2019-07-16 15:18:47 +02:00
Eren Golge 89969b0f38 LibriTTS processor and a small notification for silence trimming 2019-07-11 15:25:29 +02:00
Thomas Werkmeister 2f2482f9b4 reading all speakers upfront 2019-07-10 18:38:55 +02:00
Thomas Werkmeister d172a3d3d5 multispeaker 2019-06-26 12:59:14 +02:00
Eren Golge 118fe61028 config updates, m-ai-labs processor update. If no metafileis given parse the ffodler to use all the speakers 2019-06-21 10:20:34 +02:00
Eren Golge 037ec13453 config update, audio.py update and modularize synthesize.py 2019-06-14 16:18:49 +02:00
Eren Golge f096f1052f config updates, update audio.py, update mailabs preprocessor 2019-06-03 15:34:36 +02:00
Eren Golge d905f6e795 update mailabs preprocessor 2019-05-28 14:27:57 +02:00
Eren Golge 1654a725a7 new mozilla preprocessor 2019-05-20 18:20:48 +02:00
Eren Golge 788c8100ba bug fix for droppping cached dataset loader 2019-05-15 13:00:57 +02:00
Eren Golge 51f71c068a Merge branch 'drop_cached_dataset' of https://github.com/twerkmeister/TTS into twerkmeister-drop_cached_dataset 2019-05-14 22:37:39 +02:00
Thomas Werkmeister f9c6cde17f no cached mel/linear anymore 2019-04-29 11:26:01 +02:00
Thomas Werkmeister 7b2804cc0d dropped dataset caching 2019-04-29 11:07:04 +02:00
Eren Golge 278c7a91b7 update mozilla preprocessor 2019-04-28 14:05:06 +02:00
Eren Golge 70eabaf4d8 no exception catch for wav reading errors 2019-04-28 14:04:49 +02:00
Thomas Werkmeister 7ac66661d7 Merge branch 'dev-tacotron2' of github.com:mozilla/TTS into dev-tacotron2 2019-04-25 11:55:39 +02:00
Thomas Werkmeister f279fe9e8b removed shuffling of data in the preprocessor, uniform indentation 2019-04-25 11:46:11 +02:00
Thomas Werkmeister d1a7ad545d common voice preprocessor and tests, small refactoring within tests 2019-04-25 11:35:18 +02:00
Eren Golge add08e331b Define foldr name explicitly and mozilla preprocessor update 2019-04-24 17:36:05 +02:00
Eren Golge 8b1da591fc assert for dataloader 2019-04-18 16:25:04 +02:00
Eren Golge e05263769e small bug fix 2019-04-18 15:19:36 +02:00
Eren Golge 455667d2a4 change exception type in TTSDataset loading audio file 2019-04-12 16:12:31 +02:00
Eren Golge 9466505f27 Make eos bos chars optional 2019-04-12 16:12:15 +02:00
Eren Golge 5afd3d980b config update 2019-04-08 09:56:16 +02:00
Eren Golge 4326582bb1 TTSDataset formatting and batch sorting to use pytorch pack for rnns 2019-03-06 13:10:05 +01:00
Eren Golge cc34fe4c7c TTSDataset.py fixes and updates for existing phoneme folder in nultiprocessing 2019-02-28 17:50:43 +01:00
Eren Golge bf5f18d11e Formatting changes and distributed training 2019-02-27 09:50:52 +01:00
Eren Golge dce1715e0f tests updates 2019-02-25 18:34:06 +01:00
Eren Golge a60c9ee47d add mozilla preprocessor 2019-02-23 22:00:17 +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 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 28d45a8d80 bug fixes 2019-01-16 12:27:38 +01:00
Eren Golge 0e73b6ba45 Debug prints for phoneme extraction 2019-01-16 12:26:21 +01:00
Eren Golge 08de7a5b17 Cache phoneme transcription in a tmp folder 2019-01-16 12:25:08 +01:00