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
3,500 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

1212 Commits

Author SHA1 Message Date
Eren Gölge 2bf9e83c49 FastPitch refactor and commenting 2021-09-06 15:16:58 +00:00
Eren Gölge 59b24e66cf Add `AlignerNetwork` 2021-09-06 15:16:58 +00:00
Eren Gölge 648655fa03 Add `PitchExtractor` and return dict by `collate` 2021-09-06 15:16:58 +00:00
Eren Gölge debf772ec5 Implement binary alignment loss 2021-09-06 15:16:58 +00:00
Eren Gölge 6e9d4062f2 Add `sort_by_audio_len` option 2021-09-06 15:16:58 +00:00
Eren Gölge 59d52a4cd8 Disable autcast for criterions 2021-09-06 15:16:58 +00:00
Eren Gölge 98a7271ce8 Refactor FastPitchv2 2021-09-06 15:16:58 +00:00
Eren Gölge e429afbce4 Enable aligner for FastPitch 2021-09-06 15:16:58 +00:00
Eren Gölge 81c228a2d8 Update FastPitch don't detach duration network inputs 2021-09-06 15:16:58 +00:00
Eren Gölge ca29033ef4 Refactor FastPitch model 2021-09-06 15:16:58 +00:00
Eren Gölge 42862f7fdb Format style of the recipes 2021-09-06 15:16:58 +00:00
Eren Gölge 5d59100a88 Don't use align_score for models with duration predictor 2021-09-06 15:16:58 +00:00
Eren Gölge fac9dbe661 Update FastPitchLoss 2021-09-06 15:16:58 +00:00
Eren Gölge b81560607b Update docstrings 2021-09-06 15:16:58 +00:00
Eren Gölge 57b3aec1b9 Update docstring format 2021-09-06 15:16:58 +00:00
Eren Gölge 7692bfe7f8 Update FastPitch config 2021-09-06 15:16:58 +00:00
Eren Gölge 8584f2b82d Update docstring format 2021-09-06 15:16:58 +00:00
Eren Gölge b7caad39e0 Make optional to detach duration predictor input 2021-09-06 15:16:58 +00:00
Eren Gölge 9af42f7886 Restore `last_epoch` of the scheduler 2021-09-06 15:16:58 +00:00
Eren Gölge aacbb3ed77 Fix SpeakerManager usage in `synthesize.py` 2021-09-06 15:16:58 +00:00
Eren Gölge 545a00fc04 Use absolute paths of the attention masks 2021-09-06 15:16:58 +00:00
Eren Gölge bc396c393f Add FastPitch model and FastPitchconfig 2021-09-06 15:16:58 +00:00
Eren Gölge 5a6ffaee08 Add yin based pitch computation 2021-09-06 15:16:58 +00:00
Eren Gölge e802b24ad0 Compute mean and std pitch 2021-09-06 15:16:58 +00:00
Eren Gölge 8fffd4e813 Don't print computed phonemes 
It causes noise in logs
 2021-09-06 15:16:58 +00:00
Eren Gölge d085642ac1 Cache pitch features 
Cache the features at the beginning of `BaseTTS` training.
 2021-09-06 15:16:58 +00:00
Eren Gölge 7590c7db7a Fix `base_tacotron` `aux_input` handling 2021-09-06 15:16:58 +00:00
Eren Gölge db32162eae Fix `FastPitchLoss` 2021-09-06 15:16:58 +00:00
Eren Gölge 94e8e0d416 Fix configs 2021-09-06 15:16:58 +00:00
Eren Gölge 0f19f8c911 Fix `compute_attention_masks.py` 2021-09-06 15:16:58 +00:00
Eren Gölge 994f2be2c1 Add comput_f0 field 2021-09-06 15:16:58 +00:00
Eren Gölge c8d999b010 Add FastPitchLoss 2021-09-06 15:16:58 +00:00
Eren Gölge fba257104d Compute F0 using librosa 2021-09-06 15:16:58 +00:00
Katsuya Iida 165e5814af
Update Japanese phonemizer (#758) 
* Update default ja vocoder

* update

* Japanese phonemizer test

* Run make style

Co-authored-by: Eren Gölge <egolge@coqui.ai>
 2021-09-01 09:33:15 +02:00
Eren Gölge 2b7e55f01f Fix vits args types 2021-08-30 23:24:20 +00:00
Eren Gölge b910a6ddce Bump up to v0.2.1 2021-08-30 16:31:24 +00:00
Eren Gölge d16da949a5 Merge branch 'fix_distribute' into dev 2021-08-30 16:31:07 +00:00
Eren Gölge 6782d3eab7 Fix linter issues ofr p3.6 2021-08-30 16:18:33 +00:00
Eren Gölge 738eee0cf9 Fix style 2021-08-30 13:12:13 +00:00
Eren Gölge 5255e089e6 Fix #767 2021-08-30 13:10:08 +00:00
Eren Gölge c560114324 Fix #750 2021-08-30 13:06:50 +00:00
Eren Gölge 18b2e41e5a Use `coqui_tts` as the default run name 2021-08-30 12:56:47 +00:00
Eren Gölge 9c86f1ac68 Fix usage of abstract class in vocoders 2021-08-30 08:10:35 +00:00
Eren Gölge 18da8f5dbd Update pylint 2.10.2 and fix lint issues 2021-08-30 08:10:35 +00:00
Eren Gölge f186856e5d Add option to sort input sequnce by audio len 2021-08-30 08:10:35 +00:00
Eren Gölge 2620f62ea8 Move duration_loss inside VitsGeneratorLoss 2021-08-27 07:07:07 +00:00
Eren Gölge 1692b8e4d9
Merge pull request #726 from fijipants/patch-1 
Fix bug with log_func
 2021-08-26 22:11:29 +02:00
Eren Gölge 49e1181ea4 Fixes for the vits model 2021-08-26 17:15:09 +00:00
Eren Gölge 5911eec3b1 Small trainer refactoring 
1. Use a single Gradscaler for all the optimizers
2. Save terminal logs to a file. In DDP mode, each worker creates `trainer_N_log.txt`.
3. Fixes to allow only the main worker (rank==0) writing to Tensorboard
4. Pass parameters owned by the target optimizer to the grad_clip_norm
 2021-08-26 17:08:58 +00:00
fijipants e9e01b09b0 Fix bug with log_func 2021-08-18 19:59:51 -04:00
fijipants 8f57f8adfd Update synthesizer.py 2021-08-18 19:56:52 -04:00
Eren Gölge 3ab8cef99e Fix VITS model SPD 2021-08-18 14:55:46 +00:00
Eren Gölge c5d1dd9d1b Fix restoring best_loss 
Keep the default value if model checkpoint has no `model_loss`
 2021-08-17 12:12:36 +00:00
Eren Gölge c8bbcdfd07 Fix `test_run` for DDP 2021-08-13 19:39:02 +00:00
Eren Gölge 7c0d564965 Syncronize DDP processes 2021-08-13 10:40:50 +00:00
Eren Gölge ecf5f17dca Fix distribute.py and ddp training 2021-08-12 22:22:32 +00:00
Eren Gölge b02c4fe347 Bump up to v0.2.0 2021-08-11 08:15:39 +00:00
Eren Gölge 537bc8487a Print model count when listing modelsk 2021-08-10 16:25:11 +00:00
Eren Gölge 09ed8426e8 Add the models released with v0.2.0 2021-08-10 15:46:31 +00:00
Eren Gölge 39004484b9 Fix 🐛 
Fix synthesizer multi-speaker init
Fix #712
 2021-08-10 12:56:32 +00:00
Eren Gölge c8b9ca3d71 Fix Tacotron num_char init 2021-08-10 08:56:34 +00:00
Eren Gölge 7eb94f760b Remove Ruslan model 2021-08-09 21:48:36 +00:00
Eren Gölge 6af03ac476 Fix `num_char` init in Tacotron models 2021-08-09 21:46:15 +00:00
Ayush Chaurasia e685ddfca7 Update trainer.py 2021-08-09 18:37:46 +00:00
Ayush Chaurasia 28870f8df4 update docstring 2021-08-09 18:35:35 +00:00
Ayush Chaurasia 8a246cbb66 Update trainer.py 2021-08-09 18:35:08 +00:00
Ayush Chaurasia f3e9d61330 Refactor logging initialization 2021-08-09 18:35:08 +00:00
Ayush Chaurasia 79b74a989d Update: add_text 2021-08-09 18:34:38 +00:00
Ayush Chaurasia 9fcf48b760 Delete logger_base.py 2021-08-09 18:34:00 +00:00
Ayush Chaurasia 290972fd35 reformat 2021-08-09 18:34:00 +00:00
Ayush Chaurasia 936a47504d Update Logger API, recipes 2021-08-09 18:34:00 +00:00
Ayush Chaurasia f63cf46c55 Unified logger API 2021-08-09 18:34:00 +00:00
Ayush Chaurasia f4434da5a3 Update disabled structure 2021-08-09 18:31:16 +00:00
Ayush Chaurasia f606741dc4 Add artifacts logging , wandb args 2021-08-09 18:31:16 +00:00
Ayush Chaurasia f5e50ad502 WandbLogger 2021-08-09 18:27:06 +00:00
Eren Gölge 06018251e6 Add VITS and GlowTTS class docs 🗒️ 2021-08-09 18:02:36 +00:00
Eren Gölge 6a7275881d Add VitsConfig docstring 2021-08-09 18:02:36 +00:00
Eren Gölge f7a72552f1 Make duration predictor dropout configurable 2021-08-09 18:02:36 +00:00
Eren Gölge c312acac7d Implement VITS model 🚀 
VITS model implementation built on Glow TTS and HiFiGAN
layers.
 2021-08-09 18:02:36 +00:00
Eren Gölge 060e746e21 Add `do_amp_to_db` option 2021-08-09 18:02:36 +00:00
Eren Gölge e94c1f894d Simplify `console_logger` 2021-08-09 18:02:36 +00:00
Eren Gölge dd55960732 Update `synthesizer.py` 
Fixes and changes for multi-speaker model init and custom symbols  made
by mode.make_symbols()
 2021-08-09 18:02:36 +00:00
Eren Gölge 232a5abb6a Update `tts.setup_model` 
Run `model.make_symbols()` if availabe to set the symbol list
 2021-08-09 18:02:36 +00:00
Eren Gölge f5a6aa974f Modify `symbols.py` not to add _arpanet 2021-08-09 18:02:36 +00:00
Eren Gölge d4deb2716f Modify `get_optimizer` to accept a model argument 2021-08-09 18:02:36 +00:00
Eren Gölge 003e5579e8 Enable `custom_symbols` in text processing 
Models can define their own custom symbols lists with custom
`make_symbols()`
 2021-08-09 18:02:36 +00:00
Eren Gölge bd4e29b4dd Add `compute_linear_spec=False` to `BaseTTSConfig` 2021-08-09 18:02:36 +00:00
Eren Gölge 960a35a121 Add `scheduler_after_epoch` to `BaseTrainingConfig` 2021-08-09 18:02:36 +00:00
Eren Gölge e4648ffef1 Fix multi-speaker init of Tacotron models & tests 2021-08-09 18:02:36 +00:00
Eren Gölge 01324c8e70 Update `base_tts.py` 
Enable calling `make_symbols()` from the model if defined.
Compatibility changes for end2end `tts` models in batch formatting.
Changes in multi-speaker initialization.
Modify `test_run()` to work with dict output iof `synthesis`
 2021-08-09 18:02:36 +00:00
Eren Gölge bf562cf437 Update `trainer.py` 
Fix multi-speaker initialization of models. Add changes for end2end`tts`
models.
 2021-08-09 18:02:36 +00:00
Agrin Hilmkil ced4cfdbbf Allow saving / loading checkpoints from cloud paths (#683) 
* Allow saving / loading checkpoints from cloud paths

Allows saving and loading checkpoints directly from cloud paths like
Amazon S3 (s3://) and Google Cloud Storage (gs://) by using fsspec.

Note: The user will have to install the relevant dependency for each
protocol. Otherwise fsspec will fail and specify which dependency is
missing.

* Append suffix _fsspec to save/load function names

* Add a lower bound to the fsspec dependency

Skips the 0 major version.

* Add missing changes from refactor

* Use fsspec for remaining artifacts

* Add test case with path requiring fsspec

* Avoid writing logs to file unless output_path is local

* Document the possibility of using paths supported by fsspec

* Fix style and lint

* Add missing lint fixes

* Add type annotations to new functions

* Use Coqpit method for converting config to dict

* Fix type annotation in semi-new function

* Add return type for load_fsspec

* Fix bug where fs not always created

* Restore the experiment removal functionality
 2021-08-09 18:02:36 +00:00
Eren Gölge d9e18e009b Skip phoneme cache pre-compute if the path exists 2021-08-09 18:02:36 +00:00
Eren Gölge 6c131d168e Bump the version to 0.1.3 2021-07-26 21:32:27 +02:00
Eren Gölge febd6105b5 Update default vocoder for de-thorsten 2021-07-26 16:08:52 +02:00
Eren Gölge 4b7b88dd3d Add fullband-melgan DE vocoder 2021-07-26 15:38:30 +02:00
Eren Gölge 764f684e1b Fix `server.py` for multi-speaker models 2021-07-26 15:38:30 +02:00
Eren Gölge 75b201c6c1
Merge pull request #673 from coqui-ai/fix_stopnet 
Fix stopnet training for Tacotron models
 2021-07-24 12:25:38 +02:00
Eren Gölge fc0c4600bd Fix stopnet training 2021-07-24 11:39:54 +02:00
Eren Gölge 30eed347b6
Merge pull request #581 from Edresson/dev 
Compute speaker embeddings in batch for the LSTM  Speaker Encoder and Compute embeddings/ finding chars using config file.
 2021-07-23 17:22:51 +02:00
Edresson Casanova d5adc35fdf
Add docstring to compute_embeddings script 2021-07-21 07:16:10 -03:00
Eren Gölge 05c75aa9d5 Fix linter issues 2021-07-16 13:37:38 +02:00
Eren Gölge 58cc414477 Fix WaveGrad `test_run` 2021-07-16 13:02:25 +02:00
WeberJulian 25832eb97b Changes for review 2021-07-15 11:38:45 +02:00
Edresson b1620d1f3f remove ignore generate eval flag 2021-07-15 03:34:28 -03:00
WeberJulian c79a82ed07 refix linter 2021-07-13 23:12:18 +02:00
WeberJulian 7d92b30946 Fix tests 2021-07-13 23:00:34 +02:00
WeberJulian 32974dd6a9 Fix test sentences synthesis 2021-07-13 16:07:13 +02:00
Edresson d906fea08c lint fix and eval as argparse in extract tts spectrograms 2021-07-13 02:15:31 -03:00
Edresson 2e5baffa9c Merge fix and eval split as argparse 2021-07-13 01:47:32 -03:00
Eren Gölge 93a74cbb71
Merge pull request #628 from Aloento/patch-2 
Change to _get_preprocessor_by_name
 2021-07-11 22:17:50 +02:00
Edresson 4eac1c4651 bug fix on train_encoder and unit tests 2021-07-11 12:00:39 -03:00
Aloento 6e3e6d5756
Change to _get_preprocessor_by_name 2021-07-08 09:53:13 +02:00
Eren Gölge 8fbadad68e Bump up to v0.1.2 2021-07-06 14:44:59 +02:00
eren golge 3c0454490f Fix #616 2021-07-06 14:44:03 +02:00
Eren Gölge 0c347624e7 Bump up version to v0.1.1 2021-07-04 11:46:36 +02:00
Eren Gölge a05b234080 Raise an error when multiple GPUs are in use 
User must define the target GPU by `CUDA_VISIBLE_DEVICES` and
use `distribute.py` for multi-gpu training.
 2021-07-04 11:25:49 +02:00
Eren Gölge 270c3823eb Fix #608 2021-07-04 11:19:31 +02:00
Eren Gölge c25a2184e7 Add docs for `SpeakerManager` 2021-07-03 13:55:27 +02:00
Eren Gölge f382e4c700 Fix linter warnings 2021-07-03 13:30:24 +02:00
Eren Gölge 9e7824fe35 Fix UnivNet inference code 2021-07-02 10:48:34 +02:00
Eren Gölge 168f97cbe9 Let `Synthesizer` use the speaker manager out of the model 2021-07-02 10:47:55 +02:00
Eren Gölge 196876feb1 Fix `ModelManager` model download 2021-07-02 10:47:05 +02:00
Eren Gölge 9352cb4136 Format Align TTS docstrings 2021-07-02 10:45:58 +02:00
Eren Gölge 95ad72f38f Fix glow tts initialization 2021-07-02 10:45:37 +02:00
Eren Gölge 40b0b5365e Let `get_characters` return `num_chars` 2021-07-02 10:45:00 +02:00
Eren Gölge 0fa6a8c9b8 Fix glow tts default parameters 2021-07-02 10:44:23 +02:00
Eren Gölge a4c658f5ef Fix for using the `Synthesizer` out of the model 2021-07-02 10:43:38 +02:00
Eren Gölge db47f4f105 Update `.models.json` 2021-07-02 10:43:00 +02:00
Eren Gölge 2e1a428b83 Update glowtts docstrings and docs 2021-06-30 14:30:55 +02:00
Eren Gölge 5723eb4738 Fix config init in `process_args` 2021-06-29 16:41:08 +02:00
Eren Gölge 4b5421b42f Remove FAQ link from README.md 2021-06-29 13:20:40 +02:00
Eren Gölge 47b3b10d6d Bump up to v0.1.0 🚀 2021-06-29 13:07:59 +02:00
Eren Gölge 7ec5c31898 Merge branch 'univnet' into trainer-api 2021-06-29 10:27:12 +02:00
Eren Gölge 51398cd15b Add docstrings and typing for `audio.py` 2021-06-28 17:03:47 +02:00
Eren Gölge ae6405bb76 Docstrings for `Trainer` 2021-06-28 17:03:47 +02:00
Eren Gölge 6b265ae8e3 Docstring update 2021-06-28 17:03:47 +02:00
Eren Gölge ab563ce7cd Start training by config.json using `register_config` 2021-06-28 17:03:47 +02:00
Eren Gölge b3c073c99b Allow runing full path scripts with `distribute.py` 2021-06-28 17:03:47 +02:00
Eren Gölge d42d1c02ea Use `torch.linalg.qr` for pytorch > `v1.9.0` 2021-06-28 17:03:47 +02:00
Eren Gölge fbba37e01e Fix loading the `amp` scaler from a checkpoint 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge a7617d8ab6 Add 🐍 python 3.9 to CI 2021-06-28 17:03:47 +02:00
Eren Gölge 9790eddada Fix wrong argument name 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge 932ab107ae Docstring edit in `TTSDataset.py` ✍️ 2021-06-28 17:03:47 +02:00
Eren Gölge cfa5041db7 Fix `eval_log` for `gan.py` 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge d700845b10 Move `TorchSTFT` to `utils.audio` 2021-06-28 17:03:47 +02:00
Eren Gölge 5b89cb4fec Fixup `trainer.py` 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge 8c74f054f0 Enable support for 🐍 python 3.10 
Bump up versions numpy 1.19.5 and TF 2.5.0
 2021-06-28 17:03:47 +02:00
Eren Gölge 9455a2b01e Apply small fixes for API compatibility 2021-06-28 17:03:47 +02:00
Eren Gölge a5d5bc9063 Print `max_decoder_steps` when model reaches the limit 2021-06-28 17:03:47 +02:00