EveryVoiceTTS

[FastSpeech2] Change time.time to time.perf_counter Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#287 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

pitch calculation won't work for <16kHz audio Open

bug documentation

EveryVoiceTTS/EveryVoice#97 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

Add "watermark" to be able to identify synthesized speech Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#137 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Add model configuration validation to anticipate out-of-memory errors Open

enhancement

EveryVoiceTTS/EveryVoice#150 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

codecov does not include submodule code in the report or statistics Open

bug help wanted

EveryVoiceTTS/EveryVoice#171 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Nicely handle running out of columns in the new-project wizard Open

enhancement

EveryVoiceTTS/EveryVoice#211 · 8 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

EveryVoiceConfig constructor seems to double initialize some fields Open

bug help wanted

EveryVoiceTTS/EveryVoice#221 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026

[FastSpeech2] Error logging should have better formatting Open

EveryVoiceTTS/EveryVoice#288 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Add more unit tests for models Open

enhancement

EveryVoiceTTS/EveryVoice#227 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026

[FastSpeech2] Investigate fine-tuning of models with different pitch/energy bins Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#289 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026

We should resume from last.ckpt by default Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#247 · 2 comments · 1 reaction · 1 assignee · Indexed Sep 15, 2026

everyvoice/tests/test_cli.test_synthesize is broken Open

bug help wanted

EveryVoiceTTS/EveryVoice#258 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

[FastSpeech2] Variance can be None but it is used in `forward()` Open

EveryVoiceTTS/EveryVoice#291 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

We should warn users when their audio has no pitch Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#309 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Add denoiser to preprocessing step Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#318 · 2 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026

everyvoice segment is not robust to alignment mismatches Open

bug help wanted

EveryVoiceTTS/EveryVoice#327 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

model compilation Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#349 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 15, 2026

add documentation for adding a custom g2p engine Open

documentation

EveryVoiceTTS/EveryVoice#354 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

punctuation config should handle word-final punctuation Open

enhancement

EveryVoiceTTS/EveryVoice#355 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Add back the ability to have banned symbols Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#362 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 15, 2026

match: causes flake8 error Open

bug help wanted

EveryVoiceTTS/EveryVoice#381 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

New command to check compatibility between a filelist and a model or config as well as update the text config based on the filelist Open

enhancement

EveryVoiceTTS/EveryVoice#385 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

everyvoice segment files are being produce in the "audio" directory VS "." ( CWD) & why keep the resampled audio file once completed? Open

EveryVoiceTTS/EveryVoice#400 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026

everyvoice synthesize default file name ( ckpt or step?) Open

bug documentation

EveryVoiceTTS/EveryVoice#411 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Choose reasonable validation split Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#414 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

We should paste out the text that was synthesized in tensorboard above where the audio is printed out Open

enhancement help wanted

EveryVoiceTTS/EveryVoice#416 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

For improving EveryVoice models, we could look at reporting phoneme distribution in dataset Open

enhancement

EveryVoiceTTS/EveryVoice#420 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Filelist produces incorrect synthesized outputs with incorrect headers Open

bug question

EveryVoiceTTS/EveryVoice#437 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

PFs with nested speaker has issue Open

bug question

EveryVoiceTTS/EveryVoice#467 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Investigate zipping preprocessed files to help save inodes Open

enhancement

EveryVoiceTTS/EveryVoice#472 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026

`train_base_command()` is border line too complex according to flake8 Open

enhancement

EveryVoiceTTS/EveryVoice#474 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

`everyvoice demo` creates folders in an active directory Open

bug

EveryVoiceTTS/EveryVoice#478 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Investigate parameter pruning Open

enhancement

EveryVoiceTTS/EveryVoice#493 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

DirectoryPathMustExist and friends are not compatible with Pydantic 2.8.0 Open

bug help wanted

EveryVoiceTTS/EveryVoice#498 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Look into sharding for future-proof train/test splits Open

enhancement

EveryVoiceTTS/EveryVoice#501 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

spec-to-wav synthesis produces some errors from existing mels Open

bug

EveryVoiceTTS/EveryVoice#513 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

Fixing the build problem Open

bug needs triage

EveryVoiceTTS/transcription-playground-for-wsb#1 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 15, 2026

Improve English G2P Open

bug enhancement

EveryVoiceTTS/EveryVoice#522 · 4 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

Provide more clarity about which level of text representation is used Open

documentation

EveryVoiceTTS/EveryVoice#526 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

Resuming training for text-to-spec model does not resume with appropriate losses Open

bug

EveryVoiceTTS/EveryVoice#534 · 6 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

When doing a FP fine-tune , in Tensorboard the next round start 50 steps ahead. Open

documentation

EveryVoiceTTS/EveryVoice#550 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

Add spinner to wizard Open

enhancement

EveryVoiceTTS/EveryVoice#575 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 15, 2026

Improve the `everyvoice check-data` help Open

bug

EveryVoiceTTS/EveryVoice#577 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Create a regression Test Open

enhancement

EveryVoiceTTS/EveryVoice#611 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

Adjust default parameters to make even small samples do something Open

bug

EveryVoiceTTS/EveryVoice#628 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Empty directory created "preprocessed/YourDataSet" when training FP model Open

bug

EveryVoiceTTS/EveryVoice#641 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Schemastore does not match .json config files Open

bug

EveryVoiceTTS/EveryVoice#652 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 15, 2026

use_weighted_sampler :true --> [rank0]: KeyError: 'label' Open

bug

EveryVoiceTTS/EveryVoice#657 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 15, 2026

`everyvoice check-data` causes RuntimeError Open

EveryVoiceTTS/EveryVoice#675 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Incorporate the result of `everyvoice check-data` to be able to filter filelists Open

enhancement

EveryVoiceTTS/EveryVoice#677 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 15, 2026

Get new issues in your inbox