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

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.

examples/clone.cmd

@@ -5,7 +5,8 @@ set PATH=%~dp0..\build\Release;%PATH%
 qwen-tts.exe ^
     --model ..\models\qwen-talker-1.7b-base-Q8_0.gguf ^
     --codec ..\models\qwen-tokenizer-12hz-Q8_0.gguf ^
-    --ref-wav freeman.wav ^
+    --ref-spk freeman.spk ^
+    --ref-rvq freeman.rvq ^
     --ref-text freeman.txt ^
     --lang English ^
     -o clone.wav < prompt.txt

examples/clone.sh

@@ -5,7 +5,8 @@ set -eu
 ../build/qwen-tts \
     --model ../models/qwen-talker-1.7b-base-Q8_0.gguf \
     --codec ../models/qwen-tokenizer-12hz-Q8_0.gguf \
-    --ref-wav freeman.wav \
+    --ref-spk freeman.spk \
+    --ref-rvq freeman.rvq \
     --ref-text freeman.txt \
     --lang English \
     -o clone.wav < prompt.txt