ok

docs/MATCHA_FLOW.md

@@ -0,0 +1,24 @@
+# Matcha flow integration
+
+Style-Bert-VITS2 can optionally generate its aligned prior latent with a
+Matcha-TTS-inspired conditional flow matching (CFM) decoder. The existing
+BERT/style encoder, duration predictors, VITS normalizing flow, and waveform
+generator are retained.
+
+Set `model.use_matcha` to `true` for a newly trained or fine-tuned model. The
+template configurations enable it. Models whose configuration does not contain
+this key continue to use the original Gaussian prior sampling path.
+
+Relevant settings:
+
+- `train.c_matcha`: weight of the CFM velocity loss.
+- `model.matcha_channels`: U-Net hidden width.
+- `model.matcha_num_heads`: attention head count.
+- `model.matcha_dropout`: transformer dropout.
+- `model.matcha_sigma_min`: minimum flow path noise.
+- `model.matcha_n_timesteps`: Euler steps at inference; more steps trade speed
+  for refinement quality.
+
+The Matcha branch has new parameters, so enabling it on an existing checkpoint
+requires fine-tuning before inference. It is trained on the same random latent
+segments used by the waveform generator to keep memory use bounded.