lm_inference.py
Less than 1 minute
lm_inference.py
LM Decoding (conditional generation)
usage: lm_inference.py [-h] [--config CONFIG]
[--log_level {CRITICAL,ERROR,WARNING,INFO,DEBUG,NOTSET}]
--output_dir OUTPUT_DIR [--ngpu NGPU] [--seed SEED]
[--dtype {float16,float32,float64}]
[--num_workers NUM_WORKERS]
--data_path_and_name_and_type
DATA_PATH_AND_NAME_AND_TYPE [--key_file KEY_FILE]
[--allow_variable_data_keys ALLOW_VARIABLE_DATA_KEYS]
[--lm_train_config LM_TRAIN_CONFIG] [--lm_file LM_FILE]
[--word_lm_train_config WORD_LM_TRAIN_CONFIG]
[--word_lm_file WORD_LM_FILE] [--ngram_file NGRAM_FILE]
[--model_tag MODEL_TAG] [--quantize_lm QUANTIZE_LM]
[--quantize_modules [QUANTIZE_MODULES ...]]
[--quantize_dtype {float16,qint8}]
[--batch_size BATCH_SIZE] [--nbest NBEST]
[--beam_size BEAM_SIZE] [--penalty PENALTY]
[--maxlen MAXLEN] [--minlen MINLEN]
[--ngram_weight NGRAM_WEIGHT]
[--token_type {char,word,bpe,None}]
[--bpemodel BPEMODEL]