Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
2,869 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

722 Commits

Author SHA1 Message Date
Eren Gölge 2b529f60c8 update default hifigan config 2021-04-09 11:40:06 +02:00
Eren Gölge 105e0b4d62 vocoder gan training fixes 2021-04-09 11:38:04 +02:00
Eren Gölge 87ee6ceb57 style update #3 2021-04-09 01:17:15 +02:00
Eren Gölge 18d9ec8036 format with black 2021-04-09 00:54:59 +02:00
Eren Gölge e5b9607bc3 isort all imports 2021-04-09 00:45:20 +02:00
Eren Gölge 0e79fa86ad format with black and pylint 2.7.3 2021-04-09 00:38:08 +02:00
Eren Gölge cd69da4868 linter fixes #2 2021-04-08 16:57:46 +02:00
Eren Gölge 4d3e1e9d9a linter fix 2021-04-08 14:57:46 +02:00
Eren Gölge 53f54898bc small fixes 2021-04-08 14:22:47 +02:00
Eren Gölge 006b1d3aaa bug fix 2021-04-08 13:17:45 +02:00
Eren Gölge 3f0993aebe remove junk 2021-04-08 12:17:02 +02:00
Eren Gölge 0ee0458309 remove redundant imports 2021-04-08 11:29:15 +02:00
Eren Gölge 773f1db6fa refactor HifiGAN discriminator 2021-04-08 11:28:30 +02:00
Eren Gölge 15f362d5b1 formatting 2021-04-08 11:28:30 +02:00
Eren Gölge aee24b0704 set different seed in gan_dataset when it is multi-workers 2021-04-08 11:28:30 +02:00
Eren Gölge 6ee211c137 remove stft params causing warning 2021-04-08 11:28:30 +02:00
Eren Gölge 4998ece8d8 allow configuration of optimziers from the config file 2021-04-08 11:28:30 +02:00
Eren Gölge 8daf407652 cache empty 2021-04-08 11:28:30 +02:00
Eren Gölge 3fb78c004a move scheduler updates to the end of the epoch 2021-04-08 11:28:30 +02:00
Eren Gölge 2a872c98aa don't call os.exit as it leaves the process resources standing 2021-04-08 11:27:40 +02:00
Eren Gölge 7cecd2fb2e add hifigan D 2021-04-08 11:27:40 +02:00
Eren Gölge 13dca6e6b6 revert some of Hifigan generator updates 2021-04-08 11:27:40 +02:00
Eren Gölge 02bc776c35 prevenet grad in TorchSTFT 2021-04-08 11:27:40 +02:00
Eren Gölge cf44624df8 more docstring 2021-04-08 11:27:40 +02:00
Eren Gölge d95b1458e8 Linter fixes and docstrings for HiFiGAN 2021-04-08 11:27:40 +02:00
Eren Gölge bd7a1c177b fix #419 2021-04-08 11:26:41 +02:00
Eren Gölge 7726dfca99 change the upper bound in sound normalization 2021-04-08 11:26:01 +02:00
Eren Gölge 57f6bd1afa make using different samples for G and D networks optional 2021-04-08 11:26:01 +02:00
Eren Gölge 67f8248492 placeholder for finetuned sam hifigan model 2021-04-08 11:25:29 +02:00
Eren Gölge 241e968df1 load_checkpoint for hifigan and no_grad for inference 2021-04-08 11:25:29 +02:00
Eren Gölge de3a04f104 some commeting for Generator loss and check if the argument is defines in the config file 2021-04-08 11:25:29 +02:00
Eren Gölge ff07c5f5e3 update TorchSTFT to enable melspec 2021-04-08 11:25:29 +02:00
Eren Gölge 4a5b1d4ac2 update hifigan config 2021-04-08 11:24:21 +02:00
Eren Gölge e0e3b12b26 pass all parameters explicity to _istft 2021-04-08 11:23:20 +02:00
Eren Gölge f0e76ee135 initial models.json entry for universal hifigan 2021-04-08 11:23:20 +02:00
Eren Gölge d57f416957 small fixes 2021-04-08 11:22:30 +02:00
Eren Gölge 8c9e1c9e58 hifigan implementation update 2021-04-08 11:21:43 +02:00
Eren Gölge a14d7bc5db hifigan config update 2021-04-08 11:20:33 +02:00
Eren Gölge 8d4fd79cd7 update hifigan config 2021-04-08 11:20:33 +02:00
rishikksh20 e656e8b108 Remove select size bug 2021-04-08 11:20:33 +02:00
rishikksh20 b533474e3b Remove minor bugs and make code trainable 2021-04-08 11:20:33 +02:00
rishikksh20 ef6ff4e95c Add Exponential LR scheduler check 2021-04-08 11:20:33 +02:00
rishikksh20 1535777f64 1) Add ExponentialLR 2021-04-08 11:18:36 +02:00
rishikksh20 c20a6b1185 * Format the model definition 
* Update code and integrate training code
 2021-04-08 11:18:36 +02:00
rishikksh20 39b5845810 1) Add hifigan json files 
2) Rename MPD disc
3) Re-format remove weight norm generator
 2021-04-08 11:14:39 +02:00
rishikksh20 7b7c5d635f 1) Combine MSD with Multi-Period disc 
2) Add remove weight norm layer on Generator
 2021-04-08 11:14:39 +02:00
rishikksh20 4493feb95c Add HiFi-GAN v1 generator and discriminator classes 2021-04-08 11:14:39 +02:00
Eren Gölge c86c559349 docstring and optional padding in TorchSTFT 2021-04-07 12:36:15 +02:00
Eren Gölge f890454de3 linter fixes 2021-04-07 12:36:03 +02:00
Eren Gölge 9782d9ea5d [ci skip] implement #418 2021-04-06 16:24:50 +02:00
Eren Gölge f46a275b22 update docstring 2 2021-04-06 16:24:50 +02:00
Eren Gölge ec94ff3691 update docstring 2021-04-06 16:24:50 +02:00
Eren Gölge 2048095e9a audio.py fix 2021-04-06 16:24:50 +02:00
Eren Gölge e0b3008c31 allow choosing the log function used for amptodb conversion 2021-04-06 16:24:50 +02:00
Eren Gölge 44b4cb5ba5 DCA comment 2021-04-06 16:24:50 +02:00
Eren Gölge b86e7fb2e8 pad short samples when loading precomputed features in vocoder trainign 2021-04-06 16:24:50 +02:00
Eren Gölge 6ad4eba678 gan vocoder train fix in case of restoring models wiht no scheduler is defined 2021-04-06 16:24:50 +02:00
Eren Gölge e3ccfe37ea add DE more urls 2021-04-02 14:54:41 +02:00
Eren Gölge e84f120a04 sam-accenture model preprocessor 2021-04-01 03:41:41 +02:00
Eren Gölge e3c052382b fix loading always best_model when continue 2021-04-01 03:41:15 +02:00
Eren Gölge 48ea20e69f example aligntts config 2021-03-30 14:41:00 +02:00
Eren Gölge b4c2cf80f2 fix eval iter 2021-03-30 14:39:16 +02:00
Eren Gölge a3a840fd78 linter fixes 2021-03-30 14:39:16 +02:00
Eren Gölge 6b2e13bf62 compute normalized logp using torch primitives 2021-03-30 14:39:16 +02:00
Eren Gölge 7a382a5c2b stowed aligntts commit and small refactoring with feed_forward layers 2021-03-30 14:39:16 +02:00
Eren Gölge d542a50818 fix losses for alignTTS 2021-03-30 14:39:16 +02:00
Eren Gölge 18cc7b95ec update l1 and huber to mse loss 2021-03-30 14:39:16 +02:00
Eren Gölge 896d33ed49 update losses to hande alingtts phases 2021-03-30 14:39:16 +02:00
Eren Gölge aec0b78aff duration predictor fix 2 2021-03-30 14:39:16 +02:00
Eren Gölge 07269e639b fix duration predictor in AlignTTS 2021-03-30 14:39:16 +02:00
Eren Gölge c2d29e5cd4 FFTransformer encoder for aligntts 2021-03-30 14:39:16 +02:00
Eren Gölge 460a2d3e26 FFTransformer Decoder for AlignTTS 2021-03-30 14:39:16 +02:00
Eren Gölge 844e8e0ed4 adapt align_tts and model name handling 2021-03-30 14:39:16 +02:00
Eren Gölge aa29f5b199 aligntts loss 2021-03-30 14:39:16 +02:00
Eren Gölge a831468cab align tts MDN layer 2021-03-30 14:39:16 +02:00
Eren Gölge 4396f8e2da continue refactoring 2021-03-30 14:39:16 +02:00
Eren Gölge 892c3c3623 use torch for AngleProtoLoss 2021-03-30 14:39:16 +02:00
Eren Gölge 2b3e12ea49 correct imports after refactoring, add AlignTTS (old SSMAS) and some formatting 2021-03-30 14:39:16 +02:00
Eren Gölge ecb6b0d6ad rename GlowTtts as GlowTTS 2021-03-30 14:39:16 +02:00
Eren Gölge e8cf8cb00e restructure TF tacotron files 2021-03-30 14:39:16 +02:00
Eren Gölge 1ac99ce0d0 if git is not available set git has 'unknown' 2021-03-30 14:39:16 +02:00
Eren Gölge d9c405f0c3 create feedforward folder for SS layers 2021-03-30 14:39:16 +02:00
Eren Gölge a8cf1ae6b4 fix wavenet running with no input mask 2021-03-30 14:39:16 +02:00
Eren Gölge 1c1949d348 utf-8 encoding for certain preprocessors 2021-03-30 14:39:16 +02:00
Eren Gölge ca2f22cdd7 linter fix 2021-03-30 14:36:12 +02:00
Eren Gölge d0dcd7d1b8 let the user define outpu.wav file path fix #393 2021-03-30 14:24:31 +02:00
Eren Gölge 25654233d5 [ci skip]initial commit for the new DE models and stale ot update 2021-03-29 03:23:57 +02:00
Guy Elsmore-Paddock 15459627cc Fix `UnicodeEncodeError` on Windows Platforms 
Prevents the following error from appearing when running training on Windows platforms:
```
UnicodeEncodeError: 'charmap' codec can't encode characters in position: character maps to <undefined>
```
 2021-03-20 17:30:00 -04:00
Eren Gölge 3947750dd9 Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev 2021-03-18 14:09:47 +01:00
WeberJulian 4a9d2e4309 fix french_cleaners 2021-03-18 13:35:29 +01:00
WeberJulian 596ea2c98a Add resample script 2021-03-18 13:33:37 +01:00
Eren Gölge 6e68637f48 bug fix 2021-03-18 13:33:23 +01:00
Eren Gölge f3e5ddfaaf bug fix in preprocessor 2021-03-18 13:33:23 +01:00
Eren Gölge aeb4f82233 bug fix 2021-03-18 13:33:23 +01:00
Eren Gölge 0514330869 fix mozilla/TTS#685 2021-03-18 13:33:23 +01:00
Eren Gölge f06603a0db force utf8 2021-03-18 13:33:23 +01:00
Eren Gölge 32e8b56c45 linter fix 2021-03-18 13:33:23 +01:00
Eren Gölge 65533f33e9 fix #374 2021-03-18 13:33:00 +01:00
Eren Gölge d790d2fccb linter fix 2021-03-18 13:33:00 +01:00
WeberJulian af96080e17 fix linter issues 2021-03-18 13:33:00 +01:00
WeberJulian bf04383e74 fix french_cleaners 2021-03-18 13:33:00 +01:00
WeberJulian f6cd8e0ecc test case 2021-03-18 13:33:00 +01:00
WeberJulian e954e45e57 linter + test 2021-03-18 13:33:00 +01:00
WeberJulian e598977f3d Using path.join instead of concat 2021-03-18 13:33:00 +01:00
WeberJulian c5ef2de73f Add resample script 2021-03-18 13:33:00 +01:00
Eren Gölge 2690ab2ee5 bug fix 2021-03-16 19:15:28 +01:00
Eren Gölge 4c1aed4a9c bug fix in preprocessor 2021-03-16 19:13:32 +01:00
Eren Gölge 01e35e06c4 bug fix 2021-03-16 19:13:32 +01:00
Eren Gölge aa8bb815a7 fix mozilla/TTS#685 2021-03-16 19:13:32 +01:00
Eren Gölge a8c348ffb2 force utf8 2021-03-16 19:13:32 +01:00
Eren Gölge bf0caba0bc linter fix 2021-03-16 19:13:32 +01:00
Eren Gölge babc94f63f fix #374 2021-03-16 19:13:32 +01:00
Eren Gölge bdfd1f8a89 linter fix 2021-03-16 19:13:32 +01:00
WeberJulian 11e25a7125 fix linter issues 2021-03-16 19:13:01 +01:00
WeberJulian 1574d8dd39 fix french_cleaners 2021-03-16 19:13:01 +01:00
WeberJulian b94373afb8 test case 2021-03-16 19:13:01 +01:00
WeberJulian 93fdc0729c linter + test 2021-03-16 19:13:01 +01:00
WeberJulian 17f197f51e Using path.join instead of concat 2021-03-16 19:13:01 +01:00
WeberJulian d6749f030f Add resample script 2021-03-16 19:13:01 +01:00
Eren Gölge 838ebd6ad5 add the missing russian model 2021-03-16 18:38:35 +01:00
Eren Gölge 5c657715f2 fix #382 2021-03-16 17:31:48 +01:00
Eren Gölge 38a29ce1c9 move all models to github rls 2021-03-10 18:19:32 +01:00
Eren Gölge e5bb317242 fix model manager 2021-03-10 17:01:19 +01:00
Eren Gölge d260fb03a2 fix handling scale_stats.npy for models downloaded from Github rls 2021-03-10 16:40:30 +01:00
Eren Gölge 4aba4e5b1e linter fx 2021-03-10 15:33:11 +01:00
Eren Gölge 6c932c8503 print the desc if required parameters are not provided 2021-03-10 15:19:00 +01:00
Eren Gölge 9e84c8a623 do not copy scale_stats if exist in the output folder 2021-03-10 15:13:55 +01:00
Eren Gölge 7782034e7e fix #369 2021-03-10 15:13:21 +01:00
Eren Gölge 4337e9ff87 pad_mode in torch_stft 2021-03-10 14:41:00 +01:00
Eren Gölge 599149a7e5 downloading models from github releases 2021-03-10 11:09:01 +01:00
Eren Gölge fc19411ac6 update some of the models to github releases 2021-03-10 11:08:15 +01:00
Eren Gölge 19bb9ba851 fix tts endpoint using list-models argument 2021-03-09 14:06:09 +01:00
Eren Gölge 43379eecef fix the nl model and add the vocoder 2021-03-09 14:05:56 +01:00
r-dh 8a4dcd152f Add Dutch model 2021-03-09 13:22:19 +01:00
Eren Gölge 94805236fb Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev 2021-03-08 15:21:06 +01:00
Eren Gölge 5dcc4be560 rebrand demo server 2021-03-08 14:51:04 +01:00
Eren Gölge 947e3d6a93 rename test 2021-03-08 14:50:54 +01:00
Eren Gölge a519ed52f2 deprecate embedding models to the wheel 2021-03-08 14:06:15 +01:00
Eren Gölge c16ad38930 update server rEADME 2021-03-08 14:05:59 +01:00
Eren Gölge 594d8d8f09 linter fixes 2021-03-08 11:22:59 +01:00
Eren Gölge 00b5090974 linter fix 2021-03-08 11:05:30 +01:00
Eren Gölge e15734c3fc linter fix 2021-03-08 05:29:43 +01:00
Eren Gölge 9a48ba3821 a ton of linter updates 2021-03-08 05:06:54 +01:00
Eren Gölge e03a426378 bug fix 2021-03-08 02:59:48 +01:00
kirianguiller 628afe5cb0 remove gst handling in synthetizer.py class 2021-03-08 02:59:48 +01:00
kirianguiller 557239db7f remove re.Match typing in '_number_replace()' 2021-03-08 02:59:48 +01:00
kirianguiller 9ab07f94e2 modify according to PR reviews 2021-03-08 02:59:48 +01:00
kirianguiller 42ba30eb8f <add> Chinese mandarin implementation (tacotron2) 2021-03-08 02:59:24 +01:00
kirianguiller 49665783a6 remove gst handling in synthetizer.py class 2021-03-08 02:57:11 +01:00
kirianguiller e85658ac2b remove re.Match typing in '_number_replace()' 2021-03-08 02:57:11 +01:00
kirianguiller 0d4525322c modify according to PR reviews 2021-03-08 02:57:11 +01:00
kirianguiller e6fd118cf8 <add> Chinese mandarin implementation (tacotron2) 2021-03-08 02:57:11 +01:00
Eren Gölge e3102e753c enable backward compat for loading the best model 2021-03-08 02:57:11 +01:00
gerazov 2451a813a2 refactored keep_all_best 2021-03-08 02:57:11 +01:00
gerazov 8cefa76bae reformated docstrings in arguments.py 2021-03-08 02:57:11 +01:00
gerazov 2db40457e8 brushed up printing model load path and best loss path 2021-03-08 02:56:36 +01:00
gerazov f2e474cd37 loading last checkpoint/best_model works, deleting last best models options added, loading last best_loss added 2021-03-08 02:56:36 +01:00
Eren Gölge 4111df6769 Docstrings for audioprocessor 2021-03-08 02:54:47 +01:00
Eren Gölge 2ca74b8ab3 add RUSLAN dataset preprocessor 2021-03-08 02:54:47 +01:00
Eren Gölge 8993120634 do not test server and modelManager until fixing #657 2021-03-08 02:54:47 +01:00
Adonis Pujols 89b7f01534 add encoding="utf-8" 2021-03-08 02:54:47 +01:00
Eren Gölge ffceccb021 fix #655 2021-03-08 02:54:47 +01:00
Eren Gölge 534c341f16 linter update 2021-03-08 02:54:47 +01:00
Eren Gölge 0e1e60bef0 remove redundancy 2021-03-08 02:54:47 +01:00
Eren Gölge 93a83c0068 Update TTS/utils/arguments.py 
Co-authored-by: Jörg Thalheim <Mic92@users.noreply.github.com>
 2021-03-08 02:54:47 +01:00
Eren Gölge 39fbf2fe84 Update TTS/bin/find_unique_chars.py 
Co-authored-by: Jörg Thalheim <Mic92@users.noreply.github.com>
 2021-03-08 02:54:47 +01:00
Eren Gölge ee71eb4eb7 linter fixes 2021-03-08 02:54:47 +01:00
Eren Gölge 55fc50b26d update test_text_processing for espeak-ng 2021-03-08 02:54:47 +01:00
Eren Gölge 5b8a6736a7 remove _phoneme_punctuations 2021-03-08 02:54:47 +01:00
Eren Gölge 194f82de51 save default model chars to the training config file 2021-03-08 02:54:47 +01:00
Eren Gölge 62a8eba3b2 parse_characters function 2021-03-08 02:54:47 +01:00
Eren Gölge 0b33acdcca enable saving model characters in io.py 2021-03-08 02:54:47 +01:00
Eren Gölge f9fe167537 docstring update 2021-03-08 02:54:47 +01:00
Eren Gölge 62aeacbdd1 save used model characters to the checkpoints 2021-03-08 02:54:47 +01:00
Eren Gölge e06c93fe81 model_manager tests 2021-03-08 02:54:47 +01:00
Eren Gölge fe41084eb3 author , license and contact info in .model.json 2021-03-08 02:54:47 +01:00
nmstoker ae0d54ddae Updating models list to include EK1 TTS/vocoder 2021-03-08 02:54:47 +01:00
Eren Gölge c6702b5b9f find unique characters in a dataset 2021-03-08 02:54:47 +01:00
Eren Gölge dad3565379 use default vocoders in server.pu 2021-03-08 02:54:47 +01:00
Eren Gölge d30608ab17 set an output_sample_rate in synthesizer and use it for writing the wav 
file
 2021-03-08 02:54:47 +01:00
Eren Gölge 3ccb015cd8 return the json entry of the downloaded model 2021-03-08 02:54:47 +01:00
Eren Gölge 00e0933f43 save_wav with a custom sampling rate 2021-03-08 02:54:47 +01:00
Eren Gölge 9fefc79f0c fix make_symbols 2021-03-08 02:54:47 +01:00
Eren Gölge 8955333e9d use default vocoder in synthesize.py 2021-03-08 02:54:47 +01:00
Eren Gölge 23b282f600 define default vocoders 2021-03-08 02:54:47 +01:00
Eren Gölge 6bd8485d10 bug fix 2021-03-08 02:54:47 +01:00
Eren Gölge 5f1018abee fix spelling of a def argument and parse phonemes from config.json if 
use_phonemes is True
 2021-03-08 02:54:47 +01:00
Eren Gölge 1c1abb8a9b docstring update 2021-03-08 02:54:47 +01:00
Eren Gölge 6cd642c2e1 add missing phonemes to test_config.json 2021-03-08 02:54:47 +01:00
Eren Gölge 43b951018e fix the default vocoder name 2021-03-08 02:54:47 +01:00
Adonis Pujols 81b145c321 spelling error. should be multiband not mulitband 2021-03-08 02:54:47 +01:00
Adonis Pujols 59b1b13e07 spelling error. should be multiband not mulitband 2021-03-08 02:54:47 +01:00
Eren Gölge ee58ff2d38 add russian phoneme char 2021-03-08 02:54:47 +01:00
Eren Gölge 29d928d531 css10 dataset preprocessor 2021-03-08 02:54:47 +01:00
Eren Gölge 49771f2541 download github model releases by model manager 2021-03-08 02:54:21 +01:00
Eren Gölge 3c961370e7 linter fixes 2021-03-08 02:54:21 +01:00
gerazov 2b5cb24db7 final final fixes 2021-03-08 02:54:21 +01:00
gerazov b3c5cc2cdc final fixes 2021-03-08 02:54:21 +01:00
gerazov 10d5a63d49 updated to current dev 2021-03-08 02:54:21 +01:00
gerazov 6f06e31541 changed train scripts 2021-03-08 02:54:21 +01:00