vh f363fe6c84 fix(morpheus): raise TTS max_tokens 1200->2400 (long lines clipped at ~14.6s) ...

Cut-offs were the max_tokens=1200 ceiling (~14.6s of audio), not memory (~1250 tokens
<< 4096 context). Diagnosis: the repetition penalty is load-bearing for clean stops —
rep 1.0 => the model never emits end-of-speech and rambles to the cap; rep 1.1 (the
wrapper default) => clean natural stop. So normal lines already complete; only genuinely
long dialogue (>~14.6s, ~25+ words) hit the cap. Raised default + client max_tokens to
2400 (~29s), still within the 4096 context (no memory cost). Verified: a 49-word line
now finishes at 16.73s (was clipped at 14.6s).

2026-07-09 01:25:56 -07:00

..

mistral-small4-nvfp4

feat(tools): Mistral Small 4 NVFP4 build pipeline (quant + HF->native converter)

2026-06-17 22:19:58 -07:00

gateway-chat.html

fix(morpheus): raise TTS max_tokens 1200->2400 (long lines clipped at ~14.6s)

2026-07-09 01:25:56 -07:00