Closed roedoejet closed 1 week ago
Review changes with SemanticDiff.
Analyzed 1 of 1 files.
Filename | Status | |
---|---|---|
:heavy_check_mark: | everyvoice/model/feature_prediction/FastSpeech2_lightning | Analyzed |
CLI load time: 0:00.23
Pull Request HEAD: 35b9cdcad791619b3ff6756d887daf480ad38c81
Imports that take more than 0.1 s:
import time: self [us] | cumulative | imported package
All modified and coverable lines are covered by tests :white_check_mark:
Project coverage is 74.63%. Comparing base (
eb460a2
) to head (35b9cdc
). Report is 1 commits behind head on main.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
PR Goal?
We shouldn't require a vocoder if you're just synthesizing spectrograms. This fixes that.
Fixes?
542
Feedback sought?
sanity
Priority?
v01.0a4 (high)
Tests added?
None. Unfortunately we still don't have any unit tests for synthesis.
How to test?
try synthesizing without a vocoder (
everyvoice synthesize from-text <feature_prediction.ckpt> -t <text> -O spec
)Confidence?
high
Version change?
v01.0a4
Related PRs?
https://github.com/EveryVoiceTTS/FastSpeech2_lightning/pull/88