25 lines
1.1 KiB
Markdown
25 lines
1.1 KiB
Markdown
# 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.
|