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
4,109 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

1612 Commits

Author SHA1 Message Date
Edresson Casanova bf45319f64 Add speaker and emotion squeezer layers 2022-06-07 09:27:08 -03:00
Edresson Casanova 0f1dde642f Remove VITS conditional flow module 2022-06-06 19:48:56 -03:00
Edresson Casanova 5bd59a6023 Remove VITS End2End loss 2022-06-06 15:10:00 -03:00
Edresson Casanova 8ea72356a2 Fix Lint checks 2022-06-06 14:59:21 -03:00
Edresson Casanova 0d7f8e24b2 Add Noise scale predictor 2022-06-06 13:22:26 -03:00
Edresson Casanova cbc81b55cb Fix the VITS GAN loss 2022-06-03 13:05:40 +00:00
Edresson Casanova 7f8c12888c Add text encoder adversarial loss on the VITS 2022-06-02 18:40:57 -03:00
Edresson Casanova d9452d7038 Add end2end VITS loss 2022-06-02 13:50:08 -03:00
Edresson Casanova b7080f0f64 Recreate the prior distribution of Capacitron VAE on the right device 2022-05-27 16:41:13 -03:00
Edresson Casanova bd35371944 Add prosody encoder inference support 2022-05-27 16:00:41 -03:00
Edresson Casanova 2568b722dd Add an option to detach the prosody encoder input 2022-05-27 13:19:06 -03:00
Edresson Casanova a2aecea8f3 Add VAE prosody encoder 2022-05-27 12:53:56 -03:00
Edresson Casanova 312789edbf Condition the prosody encoder on z_p 2022-05-26 15:41:24 -03:00
Edresson Casanova e667fcb057 Support prosody conditional model on decoder input 2022-05-25 17:03:38 -03:00
Edresson Casanova 6c23398518 Add emotion classifier loss 2022-05-25 10:05:52 -03:00
Edresson Casanova 5b641ff0e3 Fix compute embeddings issue 2022-05-25 10:05:28 -03:00
Edresson Casanova d699416735 Add conditional module 2022-05-23 14:05:17 -03:00
Edresson Casanova 6e4b13c6cc Fix unit tests 2022-05-23 10:26:45 -03:00
Edresson Casanova 749b217884 Fix rebase issues 2022-05-20 18:29:39 -03:00
Edresson Casanova 1a88191a5a Disable the reversal prosody encoder speaker loss 2022-05-20 15:18:02 -03:00
Edresson Casanova 8505cd09e8 Add text encoder reversal speaker classifier loss 2022-05-20 15:18:02 -03:00
Edresson Casanova 024e567849 Clean up old code 2022-05-20 15:18:00 -03:00
Edresson Casanova dbaa71c944 Add prosody encoder params on config 2022-05-20 15:03:16 -03:00
Edresson Casanova 4107a1ef85 Add Speech style balancer 2022-05-20 14:57:40 -03:00
Edresson Casanova d49c6ab72f Add reversal classifier loss 2022-05-20 14:56:02 -03:00
Edresson Casanova 004862a79b Add prosody encoder training support 2022-05-20 14:56:02 -03:00
Edresson Casanova d9d9415513 Add emotion embedding in the encoder 2022-05-20 14:56:02 -03:00
Edresson Casanova b2b54668bc Add formatter for the Emotional Speech Dataset 2022-05-20 14:56:02 -03:00
Edresson Casanova d2b5db84f0 Remove useless encoder weights reload 2022-05-20 14:56:00 -03:00
Edresson Casanova 721a81b1d8 Fix emotion unit test 2022-05-20 14:51:26 -03:00
Edresson Casanova 01dd4e4051 Fix Style tests 2022-05-20 14:50:52 -03:00
Edresson Casanova 46762ccf35 Fix style tests 2022-05-20 14:37:43 -03:00
Edresson Casanova d8d1775273 Fix the Bug in Synthesizer 2022-05-20 14:36:28 -03:00
Edresson Casanova 39575f2937 Bug fix in single speaker emotion embedding training 2022-05-20 14:35:12 -03:00
Edresson Casanova d1ab3298ba Fix unit tests 2022-05-20 14:35:09 -03:00
Edresson Casanova a3ecaf3bdd Add emotion external embeddings training unit test 2022-05-20 14:34:22 -03:00
Edresson Casanova 5e0286c534 Add emotion consistency loss 2022-05-20 14:31:50 -03:00
Edresson Casanova e5c7ae9f1b Fix the bug in sythesizer 2022-05-20 14:31:12 -03:00
Edresson Casanova 6f95522edf Add Emotion Support for the VITS model 2022-05-20 14:31:09 -03:00
Edresson Casanova d8f5cb2674 Add emotion manager 2022-05-20 14:26:43 -03:00
a-froghyar 8be21ec387
Capacitron (#977) 
* new CI config

* initial Capacitron implementation

* delete old unused file

* fix empty formatting changes

* update losses and training script

* fix previous commit

* fix commit

* Add Capacitron test and first round of test fixes

* revert formatter change

* add changes to the synthesizer

* add stepwise gradual lr scheduler and changes to the recipe

* add inference script for dev use

* feat: add posterior inference arguments to synth methods
- added reference wav and text args for posterior inference
- some formatting

* fix: add espeak flag to base_tts and dataset APIs
- use_espeak_phonemes flag was not implemented in those APIs
- espeak is now able to be utilised for phoneme generation
- necessary phonemizer for the Capacitron model

* chore: update training script and style
- training script includes the espeak flag and other hyperparams
- made style

* chore: fix linting

* feat: add Tacotron 2 support

* leftover from dev

* chore:rename parser args

* feat: extract optimizers
- created a separate optimizer class to merge the two optimizers

* chore: revert arbitrary trainer changes

* fmt: revert formatting bug

* formatting again

* formatting fixed

* fix: log func

* fix: update optimizer
- Implemented load_state_dict for continuing training

* fix: clean optimizer init for standard models

* improvement: purge espeak flags and add training scripts

* Delete capacitronT2.py

delete old training script, new one is pushed

* feat: capacitron trainer methods
- extracted capacitron specific training  operations from the trainer into custom
methods in taco1 and taco2 models

* chore: renaming and merging capacitron and gst style args

* fix: bug fixes from the previous commit

* fix: implement state_dict method on CapacitronOptimizer

* fix: call method

* fix: inference naming

* Delete train_capacitron.py

* fix: synthesize

* feat: update tests

* chore: fix style

* Delete capacitron_inference.py

* fix: fix train tts t2 capacitron tests

* fix: double forward in T2 train step

* fix: double forward in T1 train step

* fix: run make style

* fix: remove unused import

* fix: test for T1 capacitron

* fix: make lint

* feat: add blizzard2013 recipes

* make style

* fix: update recipes

* chore: make style

* Plot test sentences in Tacotron

* chore: make style and fix import

* fix: call forward first before problematic floordiv op

* fix: update recipes

* feat: add min_audio_len to recipes

* aux_input["style_mel"]

* chore: make style

* Make capacitron T2 recipe more stable

* Remove T1 capacitron Ljspeech

* feat: implement new grad clipping routine and update configs

* make style

* Add pretrained checkpoints

* Add default vocoder

* Change trainer package

* Fix grad clip issue for tacotron

* Fix scheduler issue with tacotron

Co-authored-by: Eren Gölge <egolge@coqui.ai>
Co-authored-by: WeberJulian <julian.weber@hotmail.fr>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
 2022-05-20 16:17:11 +02:00
Edresson Casanova ee99a6c1e2 Fix voice conversion inference (#1583) 
* Add voice conversion zoo test

* Fix style

* Fix unit test
 2022-05-20 15:50:25 +02:00
Edresson Casanova e5d8ec2402
Change the VITS upsampling interpolation trick to linear (#1564) 2022-05-13 10:52:39 +02:00
Edresson Casanova c6008e5235
Add audio length sampler balancer (#1561) 
* Add audio length sampler balancer

* Add unit tests
 2022-05-12 19:59:19 +02:00
Eren Gölge 6e460b7e42
Add an assert for the upsampling trick (#1538) 2022-05-12 19:55:24 +02:00
Eren Gölge 4857967063
🐍 Python 3.10.x support and drop Python 3.6 support (#1565) 
* Update requirements

* Update CI for p3.10

* Update numpy requirement

* Drop 🐍p3.6 support

Numpy also dropped support for p3.6

* Bind cython v0.29.28

* Bind pyworld to v0.2.10

> 0.2.10 is not p3.10.x compatible

* Update Dockerfile
 2022-05-12 15:50:25 +02:00
Edresson Casanova a97eed696a
Fix the bug in eSpeak wrapper for eSpeak version 1.48.15 (#1560) 2022-05-12 15:15:18 +02:00
Eren Gölge e45ae57aef
Merge pull request #1550 from coqui-ai/fix-upsampling-asserts 
Fix VITS upsampling asserts
 2022-05-12 14:51:41 +02:00
Edresson Casanova 175ca06388 Add reinit text encoder and duration predictor parameter (#1562) 
* Add reinit encoder and duration predictor option

* Add .data to prevent any overlooked autograd hook
 2022-05-12 09:08:36 -03:00
Edresson Casanova 182711043c Fix the VITS upsampling asserts 
Fix style
 2022-05-12 09:08:29 -03:00