onmt.translate.lua

config
Read options from this file []

Data options

src
Source sequence to decode (one line per sequence) []
tgt
True target sequence (optional) []
output
Path to output the predictions (each line will be the decoded sequence [pred.txt]
model
Path to model .t7 file []

Beam Search options

beam_size
Beam size [5]
batch_size
Batch size [30]
max_sent_length
Maximum sentence length. If any sequences in srcfile are longer than this then it will error out [250]
replace_unk
Replace the generated UNK tokens with the source token thathad the highest attention weight. If phrase_table is provided,it will lookup the identified source token and give the correspondingtarget token. If it is not provided (or the identified source tokendoes not exist in the table) then it will copy the source token [false]
phrase_table
Path to source-target dictionary to replace UNKtokens. See README.md for the format this file should be in []
n_best
If > 1, it will also output an n_best list of decoded sentences [1]

Other options

gpuid
1-based identifier of the GPU to use. CPU is used when the option is < 1 [0]
time
Measure batch translation time [false]
log_file
Outputs logs to a file under this path instead of stdout. []
disable_logs
If = true, output nothing. [false]