codec: add pre-encoded voice reference (--ref-spk / --ref-rvq)

Browse Source

qwen-codec --talker extracts the speaker embedding (.spk, raw f32)
and the ICL codes (.rvq) in one pass, encode truncated to the hop
boundary conforming to the --ref-wav path. qwen-tts loads them via
--ref-spk / --ref-rvq and skips the speaker encoder and codec encode
on every synthesis: TTFA 205 ms -> 89 ms. Extends qt_tts_params with
ABI v2 latent fields, adds qt_num_codebooks(), ships freeman.spk +
freeman.rvq and switches clone scripts to the latent path. Output is
bit-identical to the raw path at fixed seed.

...

This commit is contained in:

Pascal

2026-06-11 21:45:13 +02:00

parent e8e33629c1

commit 0bf4a18b22

11 changed files with 399 additions and 144 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

examples/freeman.rvq

BIN

Binary file not shown.