Add int8 dynamic quantization support (#147)

# Add int8 dynamic quantization
 
Closes #7
 
## Summary
 
This PR implements mixed-precision int8 dynamic quantization for
pocket-tts, as requested in issue #7. It adds a `quantize=True` flag to
`TTSModel.load_model()` that reduces runtime memory usage by ~48% and
improves inference speed by ~27% on x86 and up to 23% on ARM, with no
measurable impact on audio quality.

pyproject.toml

@@ -25,6 +25,7 @@ dependencies = [
 
 [project.optional-dependencies]
 audio = ["soundfile>=0.12.0"]
+quantize = ["torchao>=0.16.0"]
 
 
 [dependency-groups]