Add int8 dynamic quantization support (#147)

Browse Source

# 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.

...

This commit is contained in:

nabil-tazi

2026-03-24 11:29:14 +01:00

committed by GitHub

parent 0dcf6cb442

commit 670e777260

8 changed files with 1506 additions and 512 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

uv.lock

Generated

+573 -508

File diff suppressed because it is too large Load Diff