diff --git a/src/languedoc/train.py b/src/languedoc/train.py --- a/src/languedoc/train.py +++ b/src/languedoc/train.py @@ -113,8 +113,9 @@ def train(data_dir: str, model_path: str lang_samples.add(text) - with gzip.open(model_path, mode="wt", encoding="utf-8") as f: - json.dump([sample_set.create_model().export() for sample_set in samples], f, ensure_ascii=False) + with gzip.GzipFile(model_path, mode="wb", mtime=0) as f: + s = json.dumps([sample_set.create_model().export() for sample_set in samples], ensure_ascii=False, sort_keys=True) + f.write(s.encode("utf-8")) print(cross_validate(samples))