Add fp16 autocast to synthesis for faster GPU throughput

The 6700 XT has significantly higher fp16 throughput than fp32.
autocast("cuda") uses fp16 for matmuls and convolutions (HiFiGAN,
S3 tokenizer, flow matching) while keeping fp32 for precision-sensitive
ops like softmax and layer norm.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

engine.py

@@ -122,7 +122,7 @@ def synthesize(
         kwargs["exaggeration"] = exaggeration
         kwargs["cfg_weight"] = cfg_weight
 
-    with torch.inference_mode():
+    with torch.inference_mode(), torch.autocast("cuda", dtype=torch.float16):
         wav = chatterbox_model.generate(text=text, **kwargs)
 
     if torch.cuda.is_available():