Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update #1

Merged
merged 255 commits into from
Nov 29, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
255 commits
Select commit Hold shift + click to select a range
d5f16d7
delete meaningless print() (#2662)
ZhouGongZaiShi Jul 4, 2023
d611067
fixed small spelling mistakes (#2551)
Woutervdvelde Jul 4, 2023
229cfbd
Update README.md
erogol Jul 4, 2023
e42a72e
Fix typo
erogol Jul 4, 2023
53938e2
Squashed commit of the following:
Jul 5, 2023
08bc758
Merge pull request #2741 from coqui-ai/merge_2651
erogol Jul 6, 2023
7b5c842
Export multispeaker onnx (#2743)
erogol Jul 6, 2023
a2984fb
Fix #2745 (#2748)
erogol Jul 7, 2023
b5cd644
Bump up to v0.15.6
erogol Jul 8, 2023
672ec3b
Fix #2749 (#2750)
erogol Jul 8, 2023
e5fb0d9
Fix share model page URL (#2757)
alex73 Jul 9, 2023
c0aabb8
Make Japanese-specific dependencies optional (#2776)
polm Jul 24, 2023
0de12ec
API tests (#2790)
erogol Jul 24, 2023
1652598
Test synthesize api separately
erogol Jul 24, 2023
f24c5e0
Update README
erogol Jul 24, 2023
6fdb88f
Add Delightful-TTS implementation (#2095)
loganhart02 Jul 24, 2023
b3472a7
Update README.md
erogol Jul 24, 2023
8aacb81
Fix Tortoise load (#2791)
erogol Jul 24, 2023
b739326
Bump up to v0.16.0
erogol Jul 24, 2023
c140df5
Adds multi-language support for VITS onnx, fixes onnx inference error…
SystemPanic Jul 31, 2023
d124f78
Recipe for Belarusian TTS (#2756)
alex73 Jul 31, 2023
9e74b51
Delightful TTS VCTK recipe fixes (#2808)
AWAS666 Jul 31, 2023
483888b
Add kwargs to ignore extra arguments w/o error (#2822)
erogol Jul 31, 2023
69f080e
Fix DelightfulTTS (#2823)
erogol Jul 31, 2023
17ddd65
Please p3.11
erogol Jul 31, 2023
dc04baa
Bump up to v0.16.1
erogol Jul 31, 2023
52a528c
add post functionality to /api/tts (#2836)
ChaseCares Aug 4, 2023
4e7f8cd
Add fairseq onnx support and strict configuration, fixes some onnx er…
SystemPanic Aug 4, 2023
48f8133
Fix imports (#2845)
erogol Aug 7, 2023
4186f42
Handle missing JA phonemizer (#2843)
erogol Aug 7, 2023
c87377b
Bump up to v0.16.2
erogol Aug 7, 2023
9a8352b
Fix import error with Bark
erogol Aug 11, 2023
37b558c
Make style
erogol Aug 11, 2023
3a104d5
Update Studio API for XTTS (#2861)
erogol Aug 13, 2023
1f9d600
Denote human voices in README.md (#2851)
michaelnew Aug 13, 2023
c4e5eff
Bump up to v0.16.3
erogol Aug 13, 2023
febcaf7
Add customizable data home path (#2871)
WeberJulian Aug 14, 2023
409db50
Add device support in TTS and Synthesizer (#2855)
jaketae Aug 14, 2023
a96562a
Update .models.json
erogol Aug 26, 2023
04a36a7
Bump up to v0.16.4
erogol Aug 26, 2023
a7a96d0
Fix loading Bark (#2893)
erogol Aug 26, 2023
c0b5e61
Bump up to v0.16.5
erogol Aug 26, 2023
fa0cbd7
Update README with new device API (#2876)
jaketae Aug 28, 2023
b79b6f0
feature: add device flag to tts cli (#2875)
jaketae Aug 28, 2023
fead04f
Add phonemizer for Belarusian language (#2856)
alex73 Aug 28, 2023
32b8ebb
Updated scipy version (#2914)
Exponefrv1 Sep 4, 2023
d1d9570
Update docs (#2919)
erogol Sep 4, 2023
40b5273
Bump up to v0.16.6
erogol Sep 4, 2023
b3b1555
Fix exception handling in manage.py (#2912)
Cohee1207 Sep 4, 2023
cdc971f
Fixed spectrogram checking on librosa 0.10.x (#2899)
T145 Sep 4, 2023
b4c8268
Add model entries
erogol Jul 24, 2023
562a950
Add BE model
erogol Sep 4, 2023
9533f86
Make style
erogol Sep 4, 2023
4d3f23b
Add CML-TTS dataset YourTTS training recipe (#2934)
Edresson Sep 12, 2023
4033db5
🔥 XTTS implementation
erogol Sep 8, 2023
5dcf9ae
Bump up v0.17.0
erogol Sep 13, 2023
ee7cee0
Fixup
erogol Sep 13, 2023
af62613
Bump up to v0.17.1
erogol Sep 13, 2023
623ea41
Fix model tests (#2943)
erogol Sep 14, 2023
44b61d2
Fixup
erogol Sep 14, 2023
ded7fd4
Make style
erogol Sep 14, 2023
13dd7c4
Bump up to v0.17.2
erogol Sep 14, 2023
9d0b76c
Check env var for COQUI_TOS_AGREED
erogol Sep 14, 2023
aa8fa47
Bump up to v0.17.4
erogol Sep 14, 2023
f829bf5
Bump version to v0.17.4 (really)
reuben Sep 15, 2023
6916aa3
Fix fsspec requirement (#2970)
WeberJulian Sep 19, 2023
335ae63
Add coqui blog post (#2949)
osanseviero Sep 19, 2023
da8b6bb
fix: xtts not taking into account device flag (#2951)
loupzeur Sep 20, 2023
dd73910
Bug: self.model_name needed to be initialized.
vltmedia Sep 23, 2023
a2a1539
fix package versions
WeberJulian Sep 25, 2023
f1c1d14
Add back umap
WeberJulian Sep 25, 2023
bbfdfbf
Update transformers to latest
WeberJulian Sep 25, 2023
089ad66
Lower the versions constraints
WeberJulian Sep 25, 2023
359755c
Merge pull request #2990 from coqui-ai/fix-TTS-install
erogol Sep 25, 2023
0b95b88
Bum up to v0.17.5
erogol Sep 25, 2023
5c047cf
Ensure `tts` CLI tool readme and usage help is in sync
akx Sep 25, 2023
0a82f06
Late-import main TTS libraries in `tts` CLI
akx Sep 25, 2023
94c5fd0
Remove unnecessary black exclude config
akx Sep 26, 2023
8bb2d65
pyproject.toml: loosen dependencies to avoid building from source
akx Sep 26, 2023
6277f09
requirements.txt: loosen pandas pin (1.4 would need to be compiled fr…
akx Sep 26, 2023
59f85a7
Remove duplicate code from xtts.tokenizer
akx Sep 26, 2023
09e14e6
Remove duplicate get_named_beta_schedules
akx Sep 26, 2023
861c68b
Rename misnamed setter
akx Sep 26, 2023
33a7c72
Merge duplicate on_train_step_start functions in delightful_tts
akx Sep 26, 2023
0dbe7cb
Remove duplicate convert_pad_shape
akx Sep 26, 2023
ea51a7f
Merge pull request #3003 from akx/duplicate-code-removal
erogol Sep 27, 2023
536a12b
Merge pull request #3001 from akx/fix-deps-again
erogol Sep 27, 2023
e39da61
Merge pull request #2999 from akx/remove-unnecessary-black-config
erogol Sep 27, 2023
8cba471
Merge pull request #2993 from akx/tts-readme
erogol Sep 27, 2023
bb05dcb
Merge pull request #2922 from coqui-ai/be_tts
erogol Sep 27, 2023
4c3c11c
Tortoise inference fix and fix zoo unit tests (#3010)
Edresson Sep 29, 2023
155c5fc
v0.17.6
erogol Sep 29, 2023
f133b9d
Upgrade and Optimize TTS Code in extractttsspectrogram.ipynb (#3012)
anupammaurya6767 Oct 2, 2023
2150136
None is not able to be read for "XTTS", fixes crash if its set to Non…
OPPEYRADY Oct 2, 2023
e5e0cbf
Streaming inference for XTTS 🚀 (#3035)
WeberJulian Oct 6, 2023
0520697
v0.17.7
erogol Oct 6, 2023
4a6103f
Redownload XTTS with the local and remote config do not match
Edresson Oct 6, 2023
ee1ef1c
Remove unused method
Edresson Oct 6, 2023
529ea3f
Print a message when it is already donwloaded
Edresson Oct 6, 2023
9965004
Try-except to present error when the user dont have connection
Edresson Oct 6, 2023
2852404
Fix style
Edresson Oct 6, 2023
0f46757
Merge pull request #3038 from coqui-ai/xtts_redonwload
gorkemgoknar Oct 6, 2023
3bb51b1
0.17.8
gorkemgoknar Oct 6, 2023
9963519
v0.17.8
gorkemgoknar Oct 6, 2023
6eaecab
fixed bugs in fastpitch tts synthesis
Aya-AlJafari Oct 11, 2023
ffddf10
unit test fix
Aya-AlJafari Oct 13, 2023
b25d96e
Merge pull request #3058 from coqui-ai/spkr_enc_3020
erogol Oct 14, 2023
e4b8d71
Update AnalyzeDataset.ipynb (#2783)
ai-coder-l Oct 16, 2023
13cd076
Synthesizer skips over embeddings file if model only has one speaker …
Oct 16, 2023
3d14642
fixed typo of docs\source\implementing_a_new_model.md (#3066)
Subash-Lamichhane Oct 16, 2023
b4666bb
fixed typo of /docs (#3065)
Subash-Lamichhane Oct 16, 2023
cae185f
Update README.md
erogol Oct 16, 2023
a151d70
Add stdout option (#3027)
David-bfg Oct 16, 2023
dcce164
Fix doc dataset (#3070)
WeberJulian Oct 16, 2023
d21f15c
fix readme (#3071)
WeberJulian Oct 17, 2023
c3b0112
Update .models.json
erogol Oct 19, 2023
bf68848
Bump up to v0.17.9
erogol Oct 19, 2023
93e6961
Update .models.json
erogol Oct 19, 2023
747f688
Bump up to v0.17.10
erogol Oct 19, 2023
cf97116
XTTS v1.1 (#3089)
WeberJulian Oct 20, 2023
85e7323
Bump up to v0.18.0
erogol Oct 20, 2023
59576fc
Bug fix on XTTS v1.1 inference (#3093)
Edresson Oct 20, 2023
414f0de
Bump up to v0.18.1
Edresson Oct 20, 2023
c7a1604
Remove global cutlet import
WeberJulian Oct 21, 2023
dad6a7b
Preserve [ja] token of the text processing
WeberJulian Oct 21, 2023
420a90e
Merge pull request #3096 from coqui-ai/fix-xtts-v1.1
erogol Oct 21, 2023
1e15269
Bump up to v0.18.2
erogol Oct 21, 2023
a32961b
Add XTTS base training code
Edresson Oct 11, 2023
40a4e63
Update mel spectrogram for the style encoder
Edresson Oct 11, 2023
47d613d
Add reproducible evaluation
Edresson Oct 13, 2023
bafab04
Add prompting masking
Edresson Oct 16, 2023
2f868dd
Bug fix on reproducible evaluation
Edresson Oct 16, 2023
c4ceaab
Add test sentences during the training
Edresson Oct 16, 2023
9e3598c
Bug Fix on inference using XTTS trainer checkpoint
Edresson Oct 18, 2023
469d624
Update LJspeech XTTS recipe
Edresson Oct 18, 2023
5f98dbe
Update Ljspeech XTTS recipe
Edresson Oct 18, 2023
94dcf84
Rename XTTS recipe
Edresson Oct 18, 2023
1f92741
Fix issue #2971
Edresson Oct 18, 2023
affaf11
Add XTTS training unit test
Edresson Oct 18, 2023
ec7f547
Rebase bug fix and update recipe
Edresson Oct 21, 2023
e8a1a50
Remove unused vars in Delightful TTS layers tests
Edresson Oct 23, 2023
653f2e7
Update xtts trainer recipe
Edresson Oct 23, 2023
8853e1c
Update XTTS recipe to only download checkpoint if it is needed
Edresson Oct 23, 2023
6fefc36
Update XTTS docs
Edresson Oct 23, 2023
1ee8096
Update XTTS docs
Edresson Oct 23, 2023
37b7945
Update XTTS train not implemented error to point to the XTTS docs
Edresson Oct 23, 2023
67ca70a
Fix Delightful TTS layers unit test
Edresson Oct 23, 2023
0f96abb
Add FT inference example on XTTS docs
Edresson Oct 23, 2023
de1d521
Update XTTS docs
Edresson Oct 23, 2023
818aa0e
Merge branch 'coqui-ai:dev' into dev
vltmedia Oct 24, 2023
8af3d2d
Add a dedicated workflow for XTTS tests
Edresson Oct 24, 2023
01839af
Bug fix on XTTS masking training
Edresson Oct 24, 2023
16ba377
Merge pull request #3086 from coqui-ai/xtts_trainer
erogol Oct 25, 2023
edd3a28
Bump up to v0.19.0
erogol Oct 25, 2023
6fa46d1
Fix get_conditioning_latents when using only ne
WeberJulian Oct 24, 2023
c113372
Move lang token add to tokenizer
WeberJulian Oct 24, 2023
d4e08c8
Add features to get_conditioning_latents
WeberJulian Oct 25, 2023
041b4b6
fix for issue 3067
Aya-AlJafari Oct 26, 2023
1c98821
Remove unused load_audio function
WeberJulian Oct 27, 2023
788959d
Merge pull request #3103 from coqui-ai/fix_xttsv1.1_again
erogol Oct 28, 2023
2d6bd71
Merge pull request #3109 from coqui-ai/tts_3067
erogol Oct 28, 2023
eccc94b
Merge pull request #2983 from vltmedia/dev
erogol Oct 28, 2023
6fef4f9
Bump up to v0.19.1
erogol Oct 30, 2023
5ae369d
Move FreeVCConfig to TTS.vc.configs (like all other config classes)
akx Oct 31, 2023
38f6f8f
Run `make style` & re-enable it in CI (#3127)
akx Nov 6, 2023
e45227d
XTTS v2.0 (#3137)
Edresson Nov 6, 2023
7eedfc6
Update README.md
erogol Nov 6, 2023
c713a83
Update VERSION
erogol Nov 6, 2023
9d54bd7
Fixup XTTS
erogol Nov 6, 2023
9bbf6eb
Drop use_ne_hifigan
erogol Nov 6, 2023
5d418bb
Update docs
erogol Nov 6, 2023
f0cb19e
Drop diffusion from XTTS (#3150)
erogol Nov 6, 2023
9942000
Update XTTS v2 recipe model files
Edresson Nov 6, 2023
459ad70
Add support for multiples speaker references on XTTS inference
Edresson Nov 6, 2023
00294ff
Update XTTS docs
Edresson Nov 6, 2023
72b2bac
Load reference in 24khz to avoid issued with multiple sr references
Edresson Nov 6, 2023
1b6f8d0
Update unit tests and recipes
Edresson Nov 6, 2023
f444f29
Add multiples references on xtts inference tests
Edresson Nov 6, 2023
b146de4
Bug fix on XTTS v2.0 Trainer
Edresson Nov 6, 2023
09fb317
Remove unused code
Edresson Nov 6, 2023
cabff9f
Update XTTS v2.0 recipe
Edresson Nov 6, 2023
13243df
Update XTTS v1.1 files
Edresson Nov 6, 2023
2470599
Drop XTTS v1
Edresson Nov 6, 2023
905900a
Update XTTS v1.1 recipe
Edresson Nov 6, 2023
5f9ab6c
Fix style
Edresson Nov 6, 2023
5e992d8
Merge pull request #3149 from coqui-ai/fixup_xtts_v2
erogol Nov 7, 2023
cbdbc44
Fix XTTS v2.0 training recipe (#3154)
Edresson Nov 7, 2023
f846a9f
Update to v0.20.1
erogol Nov 7, 2023
ce1a39a
Add char limit warn (#3130)
WeberJulian Nov 8, 2023
a24ebcd
Fix coqui api (#3168)
erogol Nov 8, 2023
cc6e9fc
Fix #3153 (#3169)
erogol Nov 8, 2023
77b1812
Merge pull request #3126 from akx/freevc-config-module
erogol Nov 8, 2023
99edd6d
Fix ModelManager.list_models() (#3128)
eginhard Nov 8, 2023
78a5966
Fix for exception on streaming if last chunk empty (#3160)
gorkemgoknar Nov 8, 2023
03ad901
Add lang code in XTTS doc (#3158)
WeberJulian Nov 8, 2023
58cb0d8
Remove v1 doc and tests (#3172)
WeberJulian Nov 8, 2023
46d9c27
Update to v0.20.2
erogol Nov 8, 2023
66a1e24
torchaudio should use proper backend to load audio (#3179)
gorkemgoknar Nov 9, 2023
1b9c400
PyTorch 2.1 Updates (Weight Norm and TorchAudio I/O) (#3176)
MattyB95 Nov 9, 2023
a8e9163
xtts/tokenizer: merge duplicate implementations of preprocess_text (#…
akx Nov 9, 2023
3b1e703
fix(formatters): set missing root_path attribute (#3182)
eginhard Nov 9, 2023
6f1cba2
Update to v0.20.3
erogol Nov 9, 2023
a16360a
Implement chunking gpt_cond
erogol Nov 13, 2023
b2682d3
Make style
erogol Nov 13, 2023
b85536b
fix max generation length
WeberJulian Nov 13, 2023
92fa988
Fixup
erogol Nov 13, 2023
f32a465
Merge pull request #3207 from coqui-ai/update_xtts_cloning
erogol Nov 13, 2023
ac3df40
Merge pull request #3208 from coqui-ai/fix_max_mel_len
erogol Nov 13, 2023
d96f388
Update to v0.20.4
erogol Nov 13, 2023
04901fb
Add speed control for inference (#3214)
WeberJulian Nov 14, 2023
15f0ac5
Update README.md (#3215)
eltociear Nov 15, 2023
73a5bd0
Fix XTTS GPT padding and inference issues (#3216)
Edresson Nov 15, 2023
88630c6
Update to v0.20.5
erogol Nov 15, 2023
3c2d5a9
Remove duplicate AudioProcessor code and fix ExtractTTSpectrogram.ipy…
eginhard Nov 16, 2023
675f983
Add sentence splitting (#3227)
WeberJulian Nov 16, 2023
fbc18b8
Fix zh bug (#3238)
WeberJulian Nov 16, 2023
7e4375d
Update to v0.20.6
erogol Nov 16, 2023
fdf0c8b
chore(encoder): remove unused code
eginhard Nov 16, 2023
39fe38b
refactor: use save_fsspec() from Trainer
eginhard Nov 16, 2023
5119e65
chore(utils.io): remove unused code
eginhard Nov 16, 2023
96678c7
refactor: use copy_model_files() from Trainer
eginhard Nov 16, 2023
0fb0d67
refactor: use save_checkpoint()/save_best_model() from Trainer
eginhard Nov 16, 2023
63d7145
Update versions
erogol Nov 17, 2023
08d11e9
Update CI version
erogol Nov 17, 2023
26efdf6
Make k_diffusion optional
erogol Nov 17, 2023
44880f0
Make style
erogol Nov 17, 2023
14579a4
Merge pull request #3248 from coqui-ai/slacker_deps
erogol Nov 17, 2023
11283fc
Ensures that only GPT model is in training mode during XTTS GPT train…
Edresson Nov 17, 2023
c864acf
Update versions
erogol Nov 17, 2023
44494da
Update CI version
erogol Nov 17, 2023
f21067a
Make k_diffusion optional
erogol Nov 17, 2023
a3279f9
Make style
erogol Nov 17, 2023
6075fa2
Ensures that only GPT model is in training mode during XTTS GPT train…
Edresson Nov 17, 2023
52cb1e2
Update model hash for v2.0.2
erogol Nov 17, 2023
c011ab7
Update to v0.20.6
erogol Nov 16, 2023
29dede2
Merge pull request #3249 from coqui-ai/run_ci_for_v0.20.6
erogol Nov 17, 2023
b47d9c6
Merge pull request #3243 from idiap/checkpoints
erogol Nov 22, 2023
64f391b
Made the tqdm `progress_bar` objects of static download methods a sta…
FlorianEagox Nov 24, 2023
4a2684b
fix(bin.synthesize): more informative error for wrong --language argu…
eginhard Nov 24, 2023
2af0220
fix: don't pass quotes to espeak (#3286)
eginhard Nov 24, 2023
8c5227e
Fix tts_with_vc (#3275)
eginhard Nov 24, 2023
4d0f53d
Misjudgment of `is_multi_lingual` When Loading Multilingual Model via…
TITC Nov 24, 2023
1bf5926
Introducing Development Dockerfile (#3263)
Kaszanas Nov 24, 2023
a55755c
update deepspeed version (#3281)
WeberJulian Nov 24, 2023
6dd43b0
Update to XTTS v2.0.3
erogol Nov 24, 2023
1542a50
Update to v0.21.0
erogol Nov 24, 2023
3206513
Simple text cleaner for "hi"
erogol Nov 24, 2023
7e57506
Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev
erogol Nov 24, 2023
00a870c
Update to v0.21.1
erogol Nov 24, 2023
11ec9f7
Add hi in config defaults
erogol Nov 24, 2023
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 53 additions & 0 deletions .github/workflows/api_tests.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
name: api_tests

on:
push:
branches:
- main
jobs:
check_skip:
runs-on: ubuntu-latest
if: "! contains(github.event.head_commit.message, '[ci skip]')"
steps:
- run: echo "${{ github.event.head_commit.message }}"

test:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: [3.9, "3.10", "3.11"]
experimental: [false]
steps:
- uses: actions/checkout@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python-version }}
architecture: x64
cache: 'pip'
cache-dependency-path: 'requirements*'
- name: check OS
run: cat /etc/os-release
- name: set ENV
run: |
export TRAINER_TELEMETRY=0
- name: Install dependencies
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends git make gcc
sudo apt-get install espeak-ng
make system-deps
- name: Install/upgrade Python setup deps
run: python3 -m pip install --upgrade pip setuptools wheel
- name: Replace scarf urls
run: |
sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
- name: Install TTS
run: |
python3 -m pip install .[all]
python3 setup.py egg_info
- name: Unit tests
run: make api_tests
env:
COQUI_STUDIO_TOKEN: ${{ secrets.COQUI_STUDIO_TOKEN }}
2 changes: 0 additions & 2 deletions .github/workflows/inference_tests.yml
Original file line number Diff line number Diff line change
Expand Up @@ -51,5 +51,3 @@ jobs:
python3 setup.py egg_info
- name: Unit tests
run: make inference_tests
env:
COQUI_STUDIO_TOKEN: ${{ secrets.COQUI_STUDIO_TOKEN }}
4 changes: 2 additions & 2 deletions .github/workflows/pypi-release.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ jobs:
build-sdist:
runs-on: ubuntu-20.04
steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v3
- name: Verify tag matches version
run: |
set -ex
Expand Down Expand Up @@ -38,7 +38,7 @@ jobs:
matrix:
python-version: ["3.9", "3.10", "3.11"]
steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v3
- uses: actions/setup-python@v2
with:
python-version: ${{ matrix.python-version }}
Expand Down
5 changes: 2 additions & 3 deletions .github/workflows/style_check.yml
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,5 @@ jobs:
run: |
python3 -m pip install .[all]
python3 setup.py egg_info
# - name: Lint check
# run: |
# make lint
- name: Style check
run: make style
53 changes: 53 additions & 0 deletions .github/workflows/tts_tests2.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
name: tts-tests2

on:
push:
branches:
- main
pull_request:
types: [opened, synchronize, reopened]
jobs:
check_skip:
runs-on: ubuntu-latest
if: "! contains(github.event.head_commit.message, '[ci skip]')"
steps:
- run: echo "${{ github.event.head_commit.message }}"

test:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: [3.9, "3.10", "3.11"]
experimental: [false]
steps:
- uses: actions/checkout@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python-version }}
architecture: x64
cache: 'pip'
cache-dependency-path: 'requirements*'
- name: check OS
run: cat /etc/os-release
- name: set ENV
run: export TRAINER_TELEMETRY=0
- name: Install dependencies
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends git make gcc
sudo apt-get install espeak
sudo apt-get install espeak-ng
make system-deps
- name: Install/upgrade Python setup deps
run: python3 -m pip install --upgrade pip setuptools wheel
- name: Replace scarf urls
run: |
sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
- name: Install TTS
run: |
python3 -m pip install .[all]
python3 setup.py egg_info
- name: Unit tests
run: make test_tts2
53 changes: 53 additions & 0 deletions .github/workflows/xtts_tests.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
name: xtts-tests

on:
push:
branches:
- main
pull_request:
types: [opened, synchronize, reopened]
jobs:
check_skip:
runs-on: ubuntu-latest
if: "! contains(github.event.head_commit.message, '[ci skip]')"
steps:
- run: echo "${{ github.event.head_commit.message }}"

test:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: [3.9, "3.10", "3.11"]
experimental: [false]
steps:
- uses: actions/checkout@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python-version }}
architecture: x64
cache: 'pip'
cache-dependency-path: 'requirements*'
- name: check OS
run: cat /etc/os-release
- name: set ENV
run: export TRAINER_TELEMETRY=0
- name: Install dependencies
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends git make gcc
sudo apt-get install espeak
sudo apt-get install espeak-ng
make system-deps
- name: Install/upgrade Python setup deps
run: python3 -m pip install --upgrade pip setuptools wheel
- name: Replace scarf urls
run: |
sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
- name: Install TTS
run: |
python3 -m pip install .[all]
python3 setup.py egg_info
- name: Unit tests
run: make test_xtts
52 changes: 52 additions & 0 deletions .github/workflows/zoo_tests_tortoise.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
name: zoo-tests-tortoise

on:
push:
branches:
- main
pull_request:
types: [opened, synchronize, reopened]
jobs:
check_skip:
runs-on: ubuntu-latest
if: "! contains(github.event.head_commit.message, '[ci skip]')"
steps:
- run: echo "${{ github.event.head_commit.message }}"

test:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: [3.9, "3.10", "3.11"]
experimental: [false]
steps:
- uses: actions/checkout@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python-version }}
architecture: x64
cache: 'pip'
cache-dependency-path: 'requirements*'
- name: check OS
run: cat /etc/os-release
- name: set ENV
run: export TRAINER_TELEMETRY=0
- name: Install dependencies
run: |
sudo apt-get update
sudo apt-get install -y git make gcc
sudo apt-get install espeak espeak-ng
make system-deps
- name: Install/upgrade Python setup deps
run: python3 -m pip install --upgrade pip setuptools wheel
- name: Replace scarf urls
run: |
sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
- name: Install TTS
run: |
python3 -m pip install .[all]
python3 setup.py egg_info
- name: Unit tests
run: nose2 -F -v -B --with-coverage --coverage TTS tests.zoo_tests.test_models.test_tortoise
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -169,3 +169,4 @@ wandb
depot/*
coqui_recipes/*
local_scripts/*
coqui_demos/*
28 changes: 27 additions & 1 deletion CONTRIBUTING.md
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ This model can be shared in two ways:

Models are served under `.models.json` file and any model is available under TTS CLI or Server end points.

Either way you choose, please make sure you send the models [here](https://github.com/coqui-ai/TTS/issues/380).
Either way you choose, please make sure you send the models [here](https://github.com/coqui-ai/TTS/discussions/930).

## Sending a ✨**PR**✨

Expand Down Expand Up @@ -128,6 +128,32 @@ The following steps are tested on an Ubuntu system.

14. Once things look perfect, We merge it to the ```dev``` branch and make it ready for the next version.

## Development in Docker container

If you prefer working within a Docker container as your development environment, you can do the following:

1. Fork 🐸TTS[https://github.com/coqui-ai/TTS] by clicking the fork button at the top right corner of the project page.

2. Clone 🐸TTS and add the main repo as a new remote named ```upsteam```.

```bash
$ git clone git@github.com:<your Github name>/TTS.git
$ cd TTS
$ git remote add upstream https://github.com/coqui-ai/TTS.git
```

3. Build the Docker Image as your development environment (it installs all of the dependencies for you):

```
docker build --tag=tts-dev:latest -f .\dockerfiles\Dockerfile.dev .
```

4. Run the container with GPU support:

```
docker run -it --gpus all tts-dev:latest /bin/bash
```

Feel free to ping us at any step you need help using our communication channels.

If you are new to Github or open-source contribution, These are good resources.
Expand Down
10 changes: 8 additions & 2 deletions Dockerfile
Original file line number Diff line number Diff line change
@@ -1,13 +1,19 @@
ARG BASE=nvidia/cuda:11.8.0-base-ubuntu22.04
FROM ${BASE}

RUN apt-get update && apt-get upgrade -y
RUN apt-get install -y --no-install-recommends gcc g++ make python3 python3-dev python3-pip python3-venv python3-wheel espeak-ng libsndfile1-dev && rm -rf /var/lib/apt/lists/*
RUN pip3 install llvmlite --ignore-installed

WORKDIR /root
COPY . /root
# Install Dependencies:
RUN pip3 install torch torchaudio --extra-index-url https://download.pytorch.org/whl/cu118
RUN rm -rf /root/.cache/pip

# Copy TTS repository contents:
WORKDIR /root
COPY . /root

RUN make install

ENTRYPOINT ["tts"]
CMD ["--help"]
9 changes: 9 additions & 0 deletions Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,12 @@ test_vocoder: ## run vocoder tests.
test_tts: ## run tts tests.
nose2 -F -v -B --with-coverage --coverage TTS tests.tts_tests

test_tts2: ## run tts tests.
nose2 -F -v -B --with-coverage --coverage TTS tests.tts_tests2

test_xtts:
nose2 -F -v -B --with-coverage --coverage TTS tests.xtts_tests

test_aux: ## run aux tests.
nose2 -F -v -B --with-coverage --coverage TTS tests.aux_tests
./run_bash_tests.sh
Expand All @@ -29,6 +35,9 @@ test_zoo: ## run zoo tests.
inference_tests: ## run inference tests.
nose2 -F -v -B --with-coverage --coverage TTS tests.inference_tests

api_tests: ## run api tests.
nose2 -F -v -B --with-coverage --coverage TTS tests.api_tests

data_tests: ## run data tests.
nose2 -F -v -B --with-coverage --coverage TTS tests.data_tests

Expand Down
Loading