Skip to content

[StyleTTS2] feat: add demo and inference integration basics#804

Merged
roedoejet merged 15 commits into
mainfrom
dev.ap/styletts2-improvements
May 28, 2026
Merged

[StyleTTS2] feat: add demo and inference integration basics#804
roedoejet merged 15 commits into
mainfrom
dev.ap/styletts2-improvements

Conversation

@roedoejet
Copy link
Copy Markdown
Member

@roedoejet roedoejet commented May 15, 2026 •
edited
Loading

PR Goal?

I previously connected the everyvoice train functionality with StyleTTS2. This PR integrates StyleTTS2 with everyvoice demo, everyvoice synthesize, and everyvoice checkpoint inspect commands.

Fixes?

Part of #686

Feedback sought?

Testing, but also sanity. I think there are actually quite a few places where we tied ourselves a bit too closely to FS2 and its architecture. I think I need some space to be able to tell how to refactor, but any insight is helpful.

I'm mostly looking for high-level analysis about whether the approach to combine repos in this way is reasonable.

Priority?

high

Tests added?

none so far

How to test?

try running everyvoice synthesize, everyvoice demo, and everyvoice checkpoint inspect. note, that I don't think this will work on the model you just trained. I'm not adding backwards compatibility support for that, although the hooks are in place for us to be able to handle this in the future in the same way as FS2

Confidence?

medium

Version change?

n/a, already bumped to 0.5.0

Related PRs?

EveryVoiceTTS/FastSpeech2_lightning#142
EveryVoiceTTS/StyleTTS2#4

@semanticdiff-com
Copy link
Copy Markdown

semanticdiff-com Bot commented May 15, 2026 •
edited
Loading

Review changes with  SemanticDiff

Changed Files
File Status
  everyvoice/tests/data/relative/config/everyvoice-text-to-wav.yaml  33% smaller
  everyvoice/tests/test_cli.py  10% smaller
  everyvoice/cli.py  9% smaller
  everyvoice/.schema/everyvoice-text-to-wav-0.5.json  4% smaller
  everyvoice/tests/stubs.py  2% smaller
  everyvoice/base_cli/checkpoint.py  0% smaller
  everyvoice/base_cli/prediction_writing_callback.py  0% smaller
  everyvoice/demo/app.py  0% smaller
  everyvoice/model/e2e/StyleTTS2_lightning  0% smaller
  everyvoice/model/feature_prediction/FastSpeech2_lightning  0% smaller
  everyvoice/wizard/basic.py  0% smaller

@roedoejet roedoejet mentioned this pull request May 15, 2026
Open
25 tasks
@roedoejet roedoejet marked this pull request as draft May 16, 2026 00:13
@roedoejet roedoejet marked this pull request as ready for review May 19, 2026 23:39
@roedoejet roedoejet requested a review from joanise May 19, 2026 23:39
@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented May 20, 2026 •
edited
Loading 

CLI load time: 0:00.23
Pull Request HEAD: 00cbb01fde49f9bce3fe0d40f6d8bc127a5ae6ab

Imports that take more than 0.1 s:
import time: self [us] | cumulative | imported package
import time:       600 |     116839 |   typer
import time:     18476 |     101618 |       multiprocessing
import time:       969 |     102587 |     everyvoice.base_cli.interfaces
import time:      1517 |     104338 |   everyvoice.base_cli.checkpoint
import time:      2120 |     117297 |           everyvoice.utils
import time:       692 |     117989 |         everyvoice.model.feature_prediction.FastSpeech2_lightning.fs2.cli.benchmark
import time:       436 |     125190 |       everyvoice.model.feature_prediction.FastSpeech2_lightning.fs2.cli.cli
import time:       252 |     125442 |     everyvoice.model.feature_prediction.FastSpeech2_lightning.fs2.cli
import time:      1111 |     126552 |   everyvoice.model.feature_prediction.FastSpeech2_lightning.fs2.cli.check_data
import time:      6881 |     439172 | everyvoice.cli
import time:     60086 |     120681 |                 importlib.metadata._text
import time:     61288 |     188456 |               importlib.metadata._adapters
import time:      6080 |     388715 |             importlib.metadata
import time:       378 |     389093 |           pygments.plugin
import time:      3356 |     395181 |         pygments.filters
import time:      3842 |     400853 |       pygments.lexer
import time:      5293 |     425632 |     rich.syntax
import time:      4298 |     480679 |   rich.markdown
import time:      3588 |     553690 | typer.rich_utils

@codecov
Copy link
Copy Markdown

codecov Bot commented May 20, 2026 •
edited
Loading

Codecov Report

❌ Patch coverage is 39.28571% with 136 lines in your changes missing coverage. Please review.
✅ Project coverage is 84.98%. Comparing base (7f0d5d4) to head (cca19c5).

Files with missing lines Patch % Lines
everyvoice/demo/app.py 3.70% 78 Missing ⚠️
everyvoice/cli.py 54.62% 50 Missing and 4 partials ⚠️
everyvoice/base_cli/checkpoint.py 20.00% 4 Missing ⚠️
Additional details and impacted files 
@@            Coverage Diff             @@
##             main     #804      +/-   ##
==========================================
- Coverage   87.55%   84.98%   -2.57%     
==========================================
  Files          45       46       +1     
  Lines        4033     4217     +184     
  Branches      605      632      +27     
==========================================
+ Hits         3531     3584      +53     
- Misses        365      494     +129     
- Partials      137      139       +2

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@roedoejet roedoejet changed the title feat: add demo and inference integration basics [StyleTTS2] feat: add demo and inference integration basics May 20, 2026
@joanise
Copy link
Copy Markdown
Member

joanise commented May 20, 2026

To resolve the conflict, keep SCHEMAS_TO_OUTPUT: and its preceding comment just before def update_schemas.

joanise
joanise reviewed May 20, 2026
View reviewed changes
Copy link
Copy Markdown
Member

@joanise joanise left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not really tested yet, but I'm done for today. Generally good but see suggestions below.

Comment thread everyvoice/demo/app.py
Comment thread everyvoice/cli.py Outdated
@roedoejet roedoejet force-pushed the dev.ap/styletts2-improvements branch 4 times, most recently from a5b2a20 to e8c84a4 Compare May 21, 2026 20:56
@roedoejet roedoejet mentioned this pull request May 21, 2026
Open
@roedoejet roedoejet requested a review from joanise May 22, 2026 18:01
@roedoejet roedoejet force-pushed the dev.ap/styletts2-improvements branch from 1ac2571 to cca19c5 Compare May 27, 2026 23:52
@roedoejet roedoejet merged commit 00cbb01 into main May 28, 2026
20 of 21 checks passed
@roedoejet roedoejet deleted the dev.ap/styletts2-improvements branch May 28, 2026 23:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@joanise joanise joanise approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@roedoejet @joanise