docs: clarify EMA weights checkpoint loading (#1292)#1301
Open
Vidit-lab wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #1292
Summary
Documentation-only fix for Issue #1292. Exactly two files changed (no functional code):
src/f5_tts/api.py — Added an init docstring to the F5TTS class warning that official checkpoints contain only EMA weights under ema_model.transformer. and that custom loaders must strip the prefix. Verified the docstring is correctly attached via AST, and the file parses as valid Python.
src/f5_tts/train/README.md — Inserted a ###⚠️ Note on Custom Checkpoint Loading block in the Training & Finetuning section, right after the existing use_ema discussion and before W&B Logging. It shows the correct inverted-filter loading snippet.