o iK:@sdZddlZddlZddlZddlZddlZddlZddlZddl m Z ddl m Z ddl mZd ddZd d Zed krHeejd ddSdS)z1Neural machine translation model training script.N) __version__) strtobool)BATCH_COUNT_CHOICESTcCs|durtjdtjtjd}|jdddd|jddd d|jd dd d|jd dtd d|jddgddd|jddtddgdd|jdt|dd|jddtdd|jd|d d!|jd"dtd#d|jd$td%d&|jd'd(d)d*d+d,|jd-d.td/d0d1|jd2d3d4td5d|jd6dtd*d7d8|jd9d:td;d|jdtdd?d1|jd@tddAd1|jdBtddCd1|jdDdEtdFd|jdGddHdIdJ|jdKtddLd1|jdMtdNdOd1|jdPdEtdQd|jdRdEtdSd|jdTdEtdUd|jdVtddWd1|jdXtddYd1|jdZdEtd[d|jd\d]td^d|jd_d`tdad|jdbd4td*dcd8|jdddet dfd|jdgdhdid4tdjd|jdkd4tdld|jdmd4tdnd|jdod4tdpd|jdqd4tdrd|jdsdtd:tdudvdw|jdxdyd:tdudzdw|jd{d4td|d|jd}d~tgddd|jddtdd|jddtdd|jddtdd|jddtdd|jddtdd|jddEtdd|jddtddgdd|jddtdd|jdddtdd|jddtd*dd8|jddtd*dd8|jddtdd|jddtdd|jddt d*dd8|jddt d*dd8|jddt d*dd8|jddtd*dd8|jdddddd|jddtd*dd8|jdddddd|jddt dd|jddt dd|S)zGet default arguments.NzOTrain a neural machine translation (NMT) model on one CPU, one or multiple GPUs) descriptionconfig_file_parser_classformatter_classz--configTzconfig file path)is_config_filehelpz --config2zCsecond config file path that overwrites the settings in `--config`.z --config3zRthird config file path that overwrites the settings in `--config` and `--config2`.z--ngpuz5Number of GPUs. If not given, use all visible devices)defaulttyper z --train-dtypefloat32)float16r float64O0O1O2O3zData type for training (only pytorch backend). O0,O1,.. flags require apex. See https://nvidia.github.io/apex/amp.html#opt-levels)r choicesr z --backendchainerpytorchzBackend library)r r rr z--outdirzOutput directory)r requiredr z --debugmode Debugmodez--dictz&Dictionary for source/target languages)rr z--seedz Random seedz --debugdirzOutput directory for debugging)r r z--resumez-r?z!Resume the training from snapshot)r nargsr z --minibatchesz-Nz-1z&Process only N minibatches (for debug))r r r z --verbosez-VrzVerbose optionz--tensorboard-dirzTensorboard log dir path)r r rr z--report-interval-itersdzReport interval iterationsz--save-interval-itersz!Save snapshot interval iterationsz --train-jsonz#Filename of train label data (json)z --valid-jsonz(Filename of validation label data (json)z--model-modulezBmodel defined module (default: espnet.nets.xxx_backend.e2e_mt:E2E)z --lsm-weightgzLabel smoothing weightz --report-bleu store_truezCompute BLEU on development set)r actionr z--nbestzOutput N-best hypothesesz --beam-sizez Beam sizez --penaltyzIncertion penaltyz --maxlenratiozInput length ratio to obtain max output length. If maxlenratio=0.0 (default), it uses a end-detect function to automatically find maximum hypothesis lengthsz --minlenratioz.Input length ratio to obtain min output lengthz--rnnlmzRNNLM model file to readz --rnnlm-confzRNNLM model config file to readz --lm-weightz RNNLM weight.z --sym-spacezz Space symbolz --sym-blankz Blank symbolz --sortagradzFHow many epochs to use sortagrad for. 0 = deactivated, -1 = all epochsz --batch-countautozKHow to count batch_size. The default (auto) will find how to count by args.z --batch-sizez --batch-seqsz-bz*Maximum seqs in a minibatch (0 to disable)z --batch-binsz*Maximum bins in a minibatch (0 to disable)z--batch-frames-inz2Maximum input frames in a minibatch (0 to disable)z--batch-frames-outz3Maximum output frames in a minibatch (0 to disable)z--batch-frames-inoutz9Maximum input+output frames in a minibatch (0 to disable)z --maxlen-inz--batch-seq-maxlen-inMLzPWhen --batch-count=seq, batch size is reduced if the input sequence length > ML.)r r metavarr z --maxlen-outz--batch-seq-maxlen-outzPWhen --batch-count=seq, batch size is reduced if the output sequence length > MLz--n-iter-processeszNumber of processes of iteratorz--optadadelta)r$adamnoam Optimizerz --accum-gradzNumber of gradient accumurationz--epsg:0yE>zEpsilon constant for optimizerz --eps-decayg{Gz?zDecaying ratio of epsilonz--lrgMbP?zLearning rate for optimizerz --lr-decayg?zDecaying ratio of learning ratez--weight-decayzWeight decay ratioz --criterionacclossz"Criterion to perform epsilon decayz --thresholdg-C6?zThreshold to stop iterationz--epochsz-ezMaximum number of epochsz--early-stop-criterionzvalidation/main/accz=Value to monitor to trigger an early stopping of the trainingz --patiencezINumber of epochs to wait without improvement before stopping the trainingz --grad-clipzGradient norm threshold to clipz--num-save-attentionz*Number of samples of attention to be savedz--context-residualFzHThe flag to switch to use context vector residual in the decoder networkz--tie-src-tgt-embeddingz8Tie parameters of source embedding and target embedding.z--tie-classifierz?Tie parameters of target embedding and output projection layer.z --enc-initz,Pre-trained ASR model to initialize encoder.z--enc-init-modszenc.enc.cfdddDS)Ncg|] }dkrt|qSrstr.0modsG/home/ubuntu/.local/lib/python3.10/site-packages/espnet/bin/mt_train.py O0get_parser....,splitr5r7r5r8Ozget_parser..z in the decoder with a target language ID (the first token in the target sequence)) configargparseArgumentParserYAMLConfigFileParserArgumentDefaultsHelpFormatteradd add_argumentintr1floatrr)parserrr7r7r8 get_parsers|   rJc Cst}||\}}|jdkr|jdkrtd|jd|jdkr0|jdvr0td|jddd lm}|j d urCd |jd }n|j }||}| || |}||_ d |j vr_d|_d|j vrgd|_t |_ |jdkrxtjtjddn tjtjddtd|jd urtjd}|d urt|d}n.tdztjddgtjtjd} Wntjtfyd}Yn wt| jdd}||_n |jdkrt d|j}t!d|t!dtjddt!d |j"t#"|j"t$j#"|j"|j%d ur;t&|j%d! } | '} Wd n 1s wYd"d#| D} | (dd$| )d%| |_*nd |_*t!d&|j|jdkrXdd'l+m,} | |d Std())zRun the main training function.rr z/chainer backend does not support --train-dtype z.Use --dtype float32.r)rrrrr z--train-dtype z" does not support the CPU backend.)dynamic_importNz espnet.nets.z_backend.e2e_mt:E2Echainer_backendpytorch_backendrz>%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s)levelformatzSkip DEBUG/INFO messagesCUDA_VISIBLE_DEVICESr<z CUDA_VISIBLE_DEVICES is not set.z nvidia-smiz-L)stdoutstderr rzsThere are some bugs with multi-GPU processing in PyTorch 1.2+ (see https://github.com/pytorch/pytorch/issues/21108)zngpu: zpython path = PYTHONPATHz(None)zrandom seed = %drbcSs g|] }|dddqS)zutf-8 r)decoder>)r3entryr7r7r8r9s zmain..r zz backend = )trainzOnly pytorch are supported.)-rJparse_known_argsbackend train_dtypeNotImplementedErrorngpu ValueErrorespnet.utils.dynamic_importrK model_module add_arguments parse_argsrversionverboselogging basicConfigINFOWARNwarningosenvirongetlenr> subprocessrunPIPECalledProcessErrorFileNotFoundErrorrRrWdebuginfoseedrandomnpdictopen readlinesinsertappend char_listespnet.mt.pytorch_backend.mtrY)cmd_argsrIargs_rKra model_classcvdr^pf dictionaryr~rYr7r7r8mainrs                       r__main__r)NT)__doc__rfrkrwrosysrAnumpyrxespnetrespnet.utils.cli_utilsrespnet.utils.training.batchfyrrJr__name__argvr7r7r7r8s$    \h