## Summary
When a single sentence exceeds `max_tokens` (50) and has no
sentence-ending punctuation (`.`, `!`, `?`), the text splitting logic
now falls back to splitting on commas, semicolons, and colons. This
prevents the model from silently skipping parts of long sentences.
Fixes#38
# 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.
-modify main,py to not hardcode using DEFAULT_VARIANT
-allow submission of path string to path of variant.yaml file saved in
custom directory in lieu of model variant identifier in CLI to use when
loading model
-addresses #57
Gabriel de Marmiesse