asr_train.py

source

Train an automatic speech recognition (ASR) model on one CPU, one or multiple GPUs

usage: asr_train.py [-h] [--config CONFIG] [--config2 CONFIG2]
                    [--config3 CONFIG3] [--ngpu NGPU] [--use-ddp]
                    [--train-dtype {float16,float32,float64,O0,O1,O2,O3}]
                    [--backend {chainer,pytorch}] --outdir OUTDIR
                    [--debugmode DEBUGMODE] --dict DICT [--seed SEED]
                    [--debugdir DEBUGDIR] [--resume [RESUME]]
                    [--minibatches MINIBATCHES] [--verbose VERBOSE]
                    [--tensorboard-dir [TENSORBOARD_DIR]]
                    [--report-interval-iters REPORT_INTERVAL_ITERS]
                    [--save-interval-iters SAVE_INTERVAL_ITERS]
                    [--train-json TRAIN_JSON] [--valid-json VALID_JSON]
                    [--model-module MODEL_MODULE] [--num-encs NUM_ENCS]
                    [--ctc_type {builtin,gtnctc,cudnnctc}]
                    [--mtlalpha MTLALPHA] [--lsm-weight LSM_WEIGHT]
                    [--report-cer] [--report-wer] [--nbest NBEST]
                    [--beam-size BEAM_SIZE] [--penalty PENALTY]
                    [--maxlenratio MAXLENRATIO] [--minlenratio MINLENRATIO]
                    [--ctc-weight CTC_WEIGHT] [--rnnlm RNNLM]
                    [--rnnlm-conf RNNLM_CONF] [--lm-weight LM_WEIGHT]
                    [--sym-space SYM_SPACE] [--sym-blank SYM_BLANK]
                    [--sortagrad [SORTAGRAD]]
                    [--batch-count {auto,seq,bin,frame}]
                    [--batch-size BATCH_SIZE] [--batch-bins BATCH_BINS]
                    [--batch-frames-in BATCH_FRAMES_IN]
                    [--batch-frames-out BATCH_FRAMES_OUT]
                    [--batch-frames-inout BATCH_FRAMES_INOUT] [--maxlen-in ML]
                    [--maxlen-out ML] [--n-iter-processes N_ITER_PROCESSES]
                    [--preprocess-conf [PREPROCESS_CONF]]
                    [--opt {adadelta,adam,noam}] [--accum-grad ACCUM_GRAD]
                    [--eps EPS] [--eps-decay EPS_DECAY]
                    [--weight-decay WEIGHT_DECAY]
                    [--criterion {loss,loss_eps_decay_only,acc}]
                    [--threshold THRESHOLD] [--epochs EPOCHS]
                    [--early-stop-criterion [EARLY_STOP_CRITERION]]
                    [--patience [PATIENCE]] [--grad-clip GRAD_CLIP]
                    [--num-save-attention NUM_SAVE_ATTENTION]
                    [--num-save-ctc NUM_SAVE_CTC] [--grad-noise GRAD_NOISE]
                    [--num-spkrs {1,2}]
                    [--context-residual [CONTEXT_RESIDUAL]]
                    [--enc-init ENC_INIT] [--enc-init-mods ENC_INIT_MODS]
                    [--dec-init DEC_INIT] [--dec-init-mods DEC_INIT_MODS]
                    [--freeze-mods FREEZE_MODS] [--use-frontend USE_FRONTEND]
                    [--use-wpe USE_WPE]
                    [--wtype {lstm,blstm,lstmp,blstmp,vgglstmp,vggblstmp,vgglstm,vggblstm,gru,bgru,grup,bgrup,vgggrup,vggbgrup,vgggru,vggbgru}]
                    [--wlayers WLAYERS] [--wunits WUNITS] [--wprojs WPROJS]
                    [--wdropout-rate WDROPOUT_RATE] [--wpe-taps WPE_TAPS]
                    [--wpe-delay WPE_DELAY]
                    [--use-dnn-mask-for-wpe USE_DNN_MASK_FOR_WPE]
                    [--use-beamformer USE_BEAMFORMER]
                    [--btype {lstm,blstm,lstmp,blstmp,vgglstmp,vggblstmp,vgglstm,vggblstm,gru,bgru,grup,bgrup,vgggrup,vggbgrup,vgggru,vggbgru}]
                    [--blayers BLAYERS] [--bunits BUNITS] [--bprojs BPROJS]
                    [--badim BADIM] [--bnmask BNMASK]
                    [--ref-channel REF_CHANNEL]
                    [--bdropout-rate BDROPOUT_RATE] [--stats-file STATS_FILE]
                    [--apply-uttmvn APPLY_UTTMVN]
                    [--uttmvn-norm-means UTTMVN_NORM_MEANS]
                    [--uttmvn-norm-vars UTTMVN_NORM_VARS]
                    [--fbank-fs FBANK_FS] [--n-mels N_MELS]
                    [--fbank-fmin FBANK_FMIN] [--fbank-fmax FBANK_FMAX]

Named Arguments