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
4,383 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

4383 Commits

Author SHA1 Message Date
Yehor Smoliakov 046b137946
Add Ukrainian LADA (female) voice 2022-12-16 12:30:44 +02:00
Eren Gölge a04db8d632
Merge pull request #2205 from coqui-ai/dev 
🚀 v0.10.0
 2022-12-15 12:02:16 +01:00
Eren G??lge 46b0ad37e7 Bump up to v0.10.0 2022-12-15 11:19:23 +01:00
Eren Gölge a9167cf239
Fixup overflow (#2218) 
* Update overflow config

* Pulling shuffle and drop_last  from config

* Print training stats for overflow
 2022-12-15 00:56:48 +01:00
Eren Gölge ecea43ec81
Adding pre-trained Overflow model (#2211) 
* Adding pretrained Overflow model

* Stabilize HMM

* Fixup model manager

* Return `audio_unique_name` by default

* Distribute max split size over datasets

* Fixup eval_split_size

* Make style
 2022-12-14 16:55:48 +01:00
Edresson Casanova 061ac43187
Add Original YourTTS vocabulary for full transfer learning (#2206) 2022-12-13 09:02:10 +01:00
Edresson Casanova 3b1a28fa95
Add YourTTS VCTK recipe (#2198) 
* Add YourTTS VCTK recipe

* Fix lint

* Add compute_embeddings and resample_files functions to be able to reuse it

* Add automatic download and speaker embedding computation for YourTTS VCTK recipe

* Add parameter for eval metadata file on compute embeddings function
 2022-12-12 16:14:25 +01:00
Shivam Mehta 3b8b105b0d
Adding OverFlow (#2183) 
* Adding encoder

* currently modifying hmm

* Adding hmm

* Adding overflow

* Adding overflow setting up flat start

* Removing runs

* adding normalization parameters

* Fixing models on same device

* Training overflow and plotting evaluations

* Adding inference

* At the end of epoch the test sentences are coming on cpu instead of gpu

* Adding figures from model during training to monitor

* reverting tacotron2 training recipe

* fixing inference on gpu for test sentences on config

* moving helpers and texts within overflows source code

* renaming to overflow

* moving loss to the model file

* Fixing the rename

* Model training but not plotting the test config sentences's audios

* Formatting logs

* Changing model name to camelcase

* Fixing test log

* Fixing plotting bug

* Adding some tests

* Adding more tests to overflow

* Adding all tests for overflow

* making changes to camel case in config

* Adding information about parameters and docstring

* removing compute_mel_statistics moved statistic computation to the model instead

* Added overflow in readme

* Adding more test cases, now it doesn't saves transition_p like tensor and can be dumped as json
 2022-12-12 12:44:15 +01:00
p0p4k 2e153d54a8
Adding missing key to formatter (#2194) 
quick fix for #2156.
 added 'root_path' key.
 2022-12-12 12:25:37 +01:00
Eren Gölge 0c9fa2229b
Update README (#2204) 2022-12-12 12:20:50 +01:00
Eren Gölge 1ddc484b49
Python API implementation (#2195) 
* Draft implementation

* Fix style

* Add api tests

* Fix lint

* Update docs

* Update tests

* Set env

* Fixup

* Fixup

* Fix lint

* Revert
 2022-12-12 12:04:20 +01:00
Eren Gölge fdeefcc612
Handle espeak 1.48.15 (#2203) 2022-12-12 11:23:45 +01:00
Eren Gölge 24620743ca
Merge pull request #2187 from coqui-ai/dev-fix-vc 2022-12-06 21:27:34 +01:00
Eren Gölge c753ad49cc
Merge pull request #2189 from coqui-ai/fix-capacitron-test 2022-12-06 21:25:06 +01:00
WeberJulian 4787a2a993 Fix capacitron test when cuda is enabled 2022-12-06 18:07:48 +01:00
Edresson Casanova d2460de94b Fix unit tests 2022-12-05 09:59:11 -03:00
Edresson Casanova ee20e30958 Fix VITS multi-speaker voice conversion inference 2022-12-05 09:15:01 -03:00
Eren Gölge 9321b22203
Fix scheduler order 2022-12-05 12:26:15 +01:00
Eren Gölge c50d89fcf7
Merge pull request #2161 from coqui-ai/tutorials 
fixed tutorial 2 incompatibility with new dev
 2022-11-21 19:08:39 +01:00
Aya be0ba934ee cleared output 2022-11-21 14:50:07 +00:00
Aya 372605180e fixet tutorial2 incompatability with new dev 2022-11-21 14:44:40 +00:00
Eren Gölge 56ba616a03
Merge pull request #1942 from coqui-ai/dev 
v0.9.0
 2022-11-16 16:50:57 +01:00
Eren G??lge bc6120c330 [ci skip]Bump up to v0.9.0 2022-11-16 16:45:02 +01:00
Julian Weber 84b9b0879e
Fix documentation (#2154) 2022-11-16 16:13:07 +01:00
logan hart ff9b63d02a
Add neon models (#2140) 
* Add neon ljspeech vits model

* Add neon german model

* Update .models.json

* Add neon spanish model

* Add french model

* Add Dutch model

* Add Hungarian model

* Add Greek model

* Remove uneeded description

* Update .models.json

* Update .models.json

* Handling neon models

* Add all neon models

* Update .models.json

* Split zoo_tests

* Update test names

* Update model testing

Co-authored-by: Eren Gölge <erogol@hotmail.com>
 2022-11-16 16:12:39 +01:00
Eren Gölge a0f31df481
Fix README.md 2022-11-16 12:27:58 +01:00
Julian Weber 3191c5f1fe
Doc update docker (#2153) 
* Complete Dockerignore to keep context managable

* Add documentation on readme

* Match pip and docker cuda version

* Use pip3 consistently
 2022-11-16 00:21:56 +01:00
Eren Gölge 4114136717
Add docker docs 2022-11-15 23:17:30 +01:00
Julian Weber f85609f9bf
Make docker images lighter (#2149) 2022-11-15 00:11:32 +01:00
Eren Gölge 7689fadd86
Remove gitter link 2022-11-14 10:44:17 +01:00
Ikko Ashimine 42edcad45f
Update README.md (#2146) 
Github -> GitHub
 2022-11-14 10:41:27 +01:00
Eren Gölge 38c99f2507
Update dep caching in actions (#2138) 2022-11-09 22:15:11 +01:00
Eren Gölge 8cb1433e6e
Cache fsspec downloads (#2132) 
* Cache fsspec downloaded files

* Use diff paths for test

* Make fsspec caching optional

* Decom GPU docker tests

* Make progress bar optional for better CI log

* Check path local
 2022-11-09 22:12:48 +01:00
Eren Gölge c5412532ac
Remove langs expect en and de (#2135) 2022-11-09 11:58:34 +01:00
Eren Gölge c16804f5d0
Add Discord server badge (#2136) 2022-11-09 11:27:07 +01:00
Eren G??lge b686c09704 Fix #2062 2022-11-07 09:22:43 +01:00
freezerain fcbfca869f
Fix back/forward slash in file path in mailabs formatter (#1938) 
* mailabs formatter: back/forward slash in file path fix

* formatters.mailabs() path rework for Windows os

* new formatter added "mailabs_win"

* lint test fix commit

* mailabs_win: removed, mailabs: "/" replaced with os.sep for windows compatibility

* Black small style fix
 2022-11-01 12:54:40 +01:00
Victor Shepardson 5307a2229b
Fix Capacitron training (#2086) 2022-11-01 12:52:06 +01:00
Ahmed Husain 5ccef6e665
Use "formatter" key in the datasets json array (#2114) 
Fix tutorial docs
 2022-11-01 12:51:16 +01:00
Marek Šuppa fa0e71d0b6
Update forward_tts.md (#2019) 
A small typo update in `forward_tts.md`
 2022-10-29 12:52:24 +02:00
CeadeS 0207071f62
Update Tutorial_2_train_your_first_TTS_model.ipynb (#2079) 
inconsistent metadata file name the metadata format example
 2022-10-25 18:36:39 +02:00
Eren Gölge ef82adcc51
Adding announcements to README.md 2022-10-15 19:11:16 +02:00
Eren Gölge dae79b0acd
Remove `/` prefix from the relative path (#2065) 2022-10-10 13:32:27 +02:00
Eren Gölge 843fa6f3fa
Check num of columns in coqui format (#2066) 
* Check 4 colums in coqui format

* Fix encoding

* Fixup
 2022-10-10 12:13:32 +02:00
Edresson Casanova f3b947e706
Minors bug fixes on VITS/YourTTS and inference (#2054) 
* Set the right device to the speaker encoder

* Bug fix on inference list_language_idxs parameter

* Bug fix on speaker encoder resample audio transform
 2022-10-06 22:23:54 +02:00
Eren Gölge 5f5d441ee5
Write non-speech files in a TXT (#2048) 
* Write non-speech files in a txt

* Save 16-bit wav out of vad
 2022-10-06 13:25:54 +02:00
Edresson Casanova d6ad9a05b4
Fix colliding dataset cache file names (#1994) 
* Fix colliding dataset cache file names

* Remove unused code
 2022-09-21 12:54:07 +02:00
Edresson Casanova 3faccbda97
Fix dataset handling with the new embedding file keys (#1991) 2022-09-19 23:44:14 +02:00
Eren Gölge 0a112f7841
Add metafile arg (#1977) 2022-09-16 14:41:49 +02:00
Eren Gölge dba2c3570a
Update readme (#1978) 2022-09-16 12:01:46 +02:00