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
4,566 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

1911 Commits

Author SHA1 Message Date
Eren Gölge edd3a28723
Bump up to v0.19.0 2023-10-25 13:29:38 +02:00
Edresson Casanova 01839af926 Bug fix on XTTS masking training 2023-10-24 18:30:14 -03:00
VLT Media 818aa0eb7e
Merge branch 'coqui-ai:dev' into dev 2023-10-23 23:36:33 -04:00
Edresson Casanova 0f96abb5ec Add FT inference example on XTTS docs 2023-10-23 13:23:30 -03:00
Edresson Casanova 37b7945474 Update XTTS train not implemented error to point to the XTTS docs 2023-10-23 11:39:17 -03:00
Edresson Casanova ec7f54768a Rebase bug fix and update recipe 2023-10-21 17:37:51 -03:00
Edresson Casanova affaf11148 Add XTTS training unit test 2023-10-21 13:41:12 -03:00
Edresson Casanova 1f92741d6a Fix issue #2971 2023-10-21 13:37:21 -03:00
Edresson Casanova 5f98dbeec9 Update Ljspeech XTTS recipe 2023-10-21 13:37:21 -03:00
Edresson Casanova 9e3598c3b7 Bug Fix on inference using XTTS trainer checkpoint 2023-10-21 13:37:21 -03:00
Edresson Casanova c4ceaabe2c Add test sentences during the training 2023-10-21 13:33:56 -03:00
Edresson Casanova 2f868dd5c2 Bug fix on reproducible evaluation 2023-10-21 13:33:56 -03:00
Edresson Casanova bafab049c2 Add prompting masking 2023-10-21 13:33:56 -03:00
Edresson Casanova 47d613df3a Add reproducible evaluation 2023-10-21 13:33:56 -03:00
Edresson Casanova 40a4e631ea Update mel spectrogram for the style encoder 2023-10-21 13:33:56 -03:00
Edresson Casanova a32961bcb4 Add XTTS base training code 2023-10-21 13:33:56 -03:00
Eren Gölge 1e152692ed
Bump up to v0.18.2 2023-10-21 17:29:53 +02:00
Julian Weber dad6a7b0b6
Preserve [ja] token of the text processing 2023-10-21 11:26:03 +02:00
Julian Weber c7a16042e3
Remove global cutlet import 2023-10-21 11:18:58 +02:00
Edresson Casanova 414f0de0a1
Bump up to v0.18.1 2023-10-20 17:30:58 -03:00
Edresson Casanova 59576fc0ec
Bug fix on XTTS v1.1 inference (#3093) 
* Bug fix on XTTS v1.1 inference

* Update .models.json

---------

Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
 2023-10-20 17:29:43 -03:00
Eren Gölge 85e7323739
Bump up to v0.18.0 2023-10-20 16:03:24 +02:00
Julian Weber cf97116185
XTTS v1.1 (#3089) 
* Add support for ne_hifigan

* Update model.json

* Update hash

* Fix model loading

* Enhance text_normalization

* Add xtts to zoo test exception

* Add model hash check

* Add get_number_tokens
 2023-10-20 16:02:08 +02:00
Eren Gölge 747f688dc3
Bump up to v0.17.10 2023-10-19 12:00:15 +02:00
Eren Gölge 93e6961bb5
Update .models.json 2023-10-19 11:59:49 +02:00
Eren Gölge bf68848f38
Bump up to v0.17.9 2023-10-19 11:22:42 +02:00
Eren Gölge c3b011217d
Update .models.json 2023-10-19 11:21:21 +02:00
David Garvey a151d70242
Add stdout option (#3027) 
* add add cli options for play and speed
--play argument uses simpleaudio to play the tts wav
--speed <float 0.0-2.0> passes speed argument to Coqui Studio models

* remove simpleaudio not referenced in file

* fix simpleaudio dependency version

* add ALSA headers for simpleaudio compilation

* Dockerfile ALSA headers for simpleaudio

* base changes to use stdout instead of play audio
Considering conversion to pipe wav data for audio playback with ohter program
like aplay.

This is incomplete code. Using to get feedback before proceeding with
implementation.

* remove play for pipe_out arg that suppresses stdout
removed play and simpleaudio dependency in place of pipe
fuctionality to allow passing wav file data to a program
dedicated to playing audio.

* scipy.io.wavfile.write fails with /dev/null target

* Streaming inference for XTTS 🚀 (#3035)

* v0.17.7

* Redownload XTTS with the local and remote config do not match

* Remove unused method

* Print a message when it is already donwloaded

* Try-except to present error when the user dont have connection

* Fix style

* 0.17.8

* v0.17.8

---------

Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
Co-authored-by: Edresson Casanova <edresson1@gmail.com>
Co-authored-by: ggoknar <ggoknar@coqui.ai>
 2023-10-16 12:07:21 +02:00
Dusty Hagstrom 13cd076a7f
Synthesizer skips over embeddings file if model only has one speaker (#2587) 
* It looks like the Neon model is special in that t does not have a speaker_name and it wants to get the only item available. This was blocking a valid model with one speaker and a d_vector_file from being executed to get the embedding.

* Update synthesizer.py

oh my how embarrassing
 2023-10-16 11:55:45 +02:00
Aya Jafari ffddf10458 unit test fix 2023-10-13 10:56:47 -03:00
Aya Jafari 6eaecab0ca fixed bugs in fastpitch tts synthesis 2023-10-10 23:02:31 -03:00
ggoknar 99635193f5 v0.17.8 2023-10-07 01:14:05 +03:00
ggoknar 3bb51b1276 0.17.8 2023-10-07 01:13:02 +03:00
Edresson Casanova 2852404bdf Fix style 2023-10-06 17:42:46 -03:00
Edresson Casanova 99650044a4 Try-except to present error when the user dont have connection 2023-10-06 17:37:05 -03:00
Edresson Casanova 529ea3f67f Print a message when it is already donwloaded 2023-10-06 17:26:40 -03:00
Edresson Casanova ee1ef1c51e Remove unused method 2023-10-06 17:21:22 -03:00
Edresson Casanova 4a6103fec9 Redownload XTTS with the local and remote config do not match 2023-10-06 17:16:30 -03:00
Eren Gölge 0520697b5f
v0.17.7 2023-10-06 18:35:26 +02:00
Julian Weber e5e0cbffc9
Streaming inference for XTTS 🚀 (#3035) 2023-10-06 18:34:06 +02:00
OPERATOR 2150136210
None is not able to be read for "XTTS", fixes crash if its set to None. (#3009) 2023-10-02 12:53:36 +02:00
Eren Gölge 155c5fc0bd
v0.17.6 2023-09-29 23:44:09 +02:00
Edresson Casanova 4c3c11c958
Tortoise inference fix and fix zoo unit tests (#3010) 2023-09-29 13:40:57 +02:00
Eren Gölge bb05dcb9b4
Merge pull request #2922 from coqui-ai/be_tts 
Adding Belarusian TTS model
 2023-09-27 09:48:28 +02:00
Eren Gölge 8cba47191f
Merge pull request #2993 from akx/tts-readme 
Ensure `tts` CLI tool readme and usage is in sync
 2023-09-27 09:46:54 +02:00
Eren Gölge ea51a7ffcc
Merge pull request #3003 from akx/duplicate-code-removal 
Duplicate code removal
 2023-09-27 09:41:35 +02:00
Aarni Koskela 0dbe7cbcc4 Remove duplicate convert_pad_shape 2023-09-27 01:10:48 +03:00
Aarni Koskela 33a7c722f6 Merge duplicate on_train_step_start functions in delightful_tts 2023-09-27 01:10:44 +03:00
Aarni Koskela 861c68b0b8 Rename misnamed setter 2023-09-27 01:09:59 +03:00
Aarni Koskela 09e14e68db Remove duplicate get_named_beta_schedules 2023-09-27 01:09:59 +03:00
Aarni Koskela 59f85a7122 Remove duplicate code from xtts.tokenizer 2023-09-27 01:09:59 +03:00
Aarni Koskela 0a82f063cc Late-import main TTS libraries in `tts` CLI 2023-09-26 15:38:56 +03:00
Aarni Koskela 5c047cf304 Ensure `tts` CLI tool readme and usage help is in sync 2023-09-26 15:38:56 +03:00
Eren Gölge 0b95b88f13
Bum up to v0.17.5 2023-09-25 18:16:45 +02:00
VLT Media dd73910651
Bug: self.model_name needed to be initialized. 
Bug: self.model_name needed to be initialize to get around a bug that automatically crashes when the user provides the model paths but no model_name when initializing the TTS object.
 2023-09-23 01:41:35 -04:00
loupzeur da8b6bbce1
fix: xtts not taking into account device flag (#2951) 
* fix: xtts not taking into account device flag

* Style changes

---------

Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
 2023-09-20 09:57:02 +02:00
Reuben Morais f829bf50f8
Bump version to v0.17.4 (really) 2023-09-15 16:40:34 +02:00
Eren G??lge aa8fa4756e Bump up to v0.17.4 2023-09-14 17:52:44 +02:00
Eren G??lge 9d0b76ce23 Check env var for COQUI_TOS_AGREED 2023-09-14 17:51:40 +02:00
Eren G??lge 13dd7c4c9e Bump up to v0.17.2 2023-09-14 15:24:05 +02:00
Eren G??lge ded7fd4fb2 Make style 2023-09-14 15:23:37 +02:00
Eren G??lge 44b61d2b92 Fixup 2023-09-14 15:22:54 +02:00
Eren Gölge 623ea41634
Fix model tests (#2943) 2023-09-14 15:21:48 +02:00
Eren G??lge af62613c86 Bump up to v0.17.1 2023-09-13 18:23:39 +02:00
Eren G??lge ee7cee0e35 Fixup 2023-09-13 18:21:44 +02:00
Eren G??lge 5dcf9ae311 Bump up v0.17.0 2023-09-13 18:04:26 +02:00
Eren Gölge 4033db5f4b 🔥 XTTS implementation 2023-09-13 17:51:24 +02:00
Edresson Casanova 4d3f23b5d3
Add CML-TTS dataset YourTTS training recipe (#2934) 2023-09-12 11:49:14 +02:00
Eren Gölge 9533f8656c Make style 2023-09-04 13:58:37 +02:00
Eren Gölge 562a9509f2 Add BE model 2023-09-04 13:57:03 +02:00
Eren Gölge b4c82685a7 Add model entries 2023-09-04 13:04:58 +02:00
Cohee b3b1555d82
Fix exception handling in manage.py (#2912) 2023-09-04 12:54:30 +02:00
Eren G??lge 40b527345f Bump up to v0.16.6 2023-09-04 12:51:53 +02:00
Aleś Bułojčyk fead04f779
Add phonemizer for Belarusian language (#2856) 2023-08-28 11:20:45 +02:00
Jake Tae b79b6f0762
feature: add device flag to tts cli (#2875) 2023-08-28 11:20:12 +02:00
Eren Gölge c0b5e61749
Bump up to v0.16.5 2023-08-26 12:00:25 +02:00
Eren Gölge a7a96d08dd
Fix loading Bark (#2893) 
* Fixup hubert path

* Make style
 2023-08-26 11:59:00 +02:00
Eren Gölge 04a36a727b
Bump up to v0.16.4 2023-08-26 10:39:48 +02:00
Eren Gölge a96562a750
Update .models.json 2023-08-26 10:36:40 +02:00
Jake Tae 409db505d2
Add device support in TTS and Synthesizer (#2855) 
* fix: resolve merge conflicts

* fix: retain backwards compatability in functions

* feature: utilize device for voice transfer

* feature: use device for vocoder

* chore: cleanup vocoder cpu logic

* fix: add necessary vocoder output device check

* fix: add necessary vocoder output device check

* fix: indentation

* fix: check if waveform is pt tensor before cpu conversion

---------

Co-authored-by: Jake Tae <jaketae@Jakes-MacBook-Pro-2.local>
 2023-08-14 21:04:44 +02:00
Julian Weber febcaf710a
Add customizable data home path (#2871) 
* Add customizable data home path

* Add TTS_HOME as an option
 2023-08-14 21:02:48 +02:00
Eren Gölge c4e5effab9 Bump up to v0.16.3 2023-08-13 12:22:04 +02:00
Eren Gölge 3a104d5c49
Update Studio API for XTTS (#2861) 
* Update Studio API for XTTS

* Update the docs

* Update README.md

* Update README.md

Update README
 2023-08-13 12:04:12 +02:00
Eren G??lge 37b558ccb9 Make style 2023-08-11 12:55:23 +02:00
Eren G??lge 9a8352b8da Fix import error with Bark 2023-08-11 03:33:59 +02:00
Eren Gölge c87377b713
Bump up to v0.16.2 2023-08-07 13:21:14 +02:00
Eren Gölge 4186f42b21
Handle missing JA phonemizer (#2843) 
* Handle missing JA phonemizer

* Make style
 2023-08-07 13:19:38 +02:00
Javier 4e7f8cd021
Add fairseq onnx support and strict configuration, fixes some onnx errors (#2831) 2023-08-04 11:02:59 +02:00
ChaseC 52a528cfcf
add post functionality to /api/tts (#2836) 2023-08-04 10:54:20 +02:00
Eren Gölge dc04baa1ee
Bump up to v0.16.1 2023-07-31 15:54:45 +02:00
Eren Gölge 17ddd65741 Please p3.11 2023-07-31 15:53:19 +02:00
Eren Gölge 69f080eb47
Fix DelightfulTTS (#2823) 
* Fix tests

* Make style
 2023-07-31 13:52:45 +02:00
Eren Gölge 483888b9d8
Add kwargs to ignore extra arguments w/o error (#2822) 2023-07-31 11:37:35 +02:00
Aleś Bułojčyk d124f78430
Recipe for Belarusian TTS (#2756) 
* Changes from jhlfrfufyfn <jhlfrfufyfn@gmail.com>

* Recipe for Belarusian TTS

---------

Co-authored-by: jhlfrfufyfn <jhlfrfufyfn@gmail.com>
 2023-07-31 10:26:21 +02:00
Javier c140df5a58
Adds multi-language support for VITS onnx, fixes onnx inference error when speaker_id is None or not passed, fixes onnx exporting for models with init_discriminator=false (#2816) 2023-07-31 10:19:49 +02:00
Eren Gölge b739326503
Bump up to v0.16.0 2023-07-24 16:04:10 +02:00
Eren Gölge 8aacb81849
Fix Tortoise load (#2791) 
* Remove key prunning in tortoise

* Make lint
 2023-07-24 13:42:47 +02:00
logan hart 6fdb88f8e2
Add Delightful-TTS implementation (#2095) 
* add configs

* Update config file

* Add model configs

* Add model layers

* Add layer files

* Add layer modules

* change config names

* Add emotion manager

* fIX missing ap bug

* Fix missing ap bug

* Add base TTS e2e class

* Fix wrong variable name in load_tts_samples

* Add training script

* Remove range predictor and gaussian upsampling

* Add helper function

* Add vctk recipe

* Add conformer docs

* Fix linting in conformer.py

* Add Docs

* remove duplicate import

* refactor args

* Fix bugs

* Removew emotion embedding

* remove unused arg

* Remove emotion embedding arg

* Remove emotion embedding arg

* fix style issues

* Fix bugs

* Fix bugs

* Add unittests

* make style

* fix formatter bug

* fix test

* Add pyworld compute pitch func

* Update requirments.txt

* Fix dataset Bug

* Chnge layer norm to instance norm

* Add missing import

* Remove emotions.py

* remove ssim loss

* Add init layers func to aligner

* refactor model layers

* remove audio_config arg

* Rename loss func

* Rename to delightful-tts

* Rename loss func

* Remove unused modules

* refactor imports

* replace audio config with audio processor

* Add change sample rate option

* remove broken resample func

* update recipe

* fix style, add config docs

* fix tests and multispeaker embd dim

* remove pyworld

* Make style and fix inference

* Split tts tests

* Fixup

* Fixup

* Fixup

* Add argument names

* Set "random" speaker in the model Tortoise/Bark

* Use a diff f0_cache path for delightfull tts

* Fix delightful speaker handling

* Fix lint

* Make style

---------

Co-authored-by: loganhart420 <loganartpersonal@gmail.com>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
 2023-07-24 13:41:26 +02:00
Eren Gölge 0de12ec5aa
API tests (#2790) 
* Separate API tests and only run when uplifted

* Make style
 2023-07-24 12:14:21 +02:00
Paul O'Leary McCann c0aabb8596
Make Japanese-specific dependencies optional (#2776) 
* Don't install MeCab by default

* Add optional [ja] deps, like [dev] etc

* Add JA requirements file

* Add JA requirements to requirements_all

This should help the tests run.
 2023-07-24 11:28:27 +02:00