v0.3.0
- Implement the distilled
small100model by Mohammadshahi et al. (2022) and use this model by default. - Enable half-precision inference for
m2m100models andsmall100by default; see experiments/results/summary.md for benchmark results
small100 model by Mohammadshahi et al. (2022) and use this model by default.m2m100 models and small100 by default; see experiments/results/summary.md for benchmark results