spk_embed_extract.py

Less than 1 minute
spk_embed_extract.py

speaker embedding extraction
usage: spk_embed_extract.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
                            [--batch_type {unsorted,sorted,folded,length,numel}]
                            [--batch_bins BATCH_BINS]
                            [--valid_batch_bins VALID_BATCH_BINS]
                            [--valid_batch_type {unsorted,sorted,folded,length,numel,None}]
                            [--max_cache_size MAX_CACHE_SIZE]
                            [--max_cache_fd MAX_CACHE_FD]
                            [--allow_multi_rates ALLOW_MULTI_RATES]
                            [--valid_max_cache_size VALID_MAX_CACHE_SIZE]
                            [--shape_file SHAPE_FILE]
                            [--input_size INPUT_SIZE]
                            [--num_cohort_spk NUM_COHORT_SPK]
                            [--num_utt_per_spk NUM_UTT_PER_SPK]
                            [--utt_select_sec UTT_SELECT_SEC]
                            [--average_spk AVERAGE_SPK]
                            [--adaptive_cohort_size ADAPTIVE_COHORT_SIZE]
                            [--qmf_dur_thresh QMF_DUR_THRESH]
                            [--qmf_num_trial_per_condition QMF_NUM_TRIAL_PER_CONDITION]
                            [--allow_variable_data_keys ALLOW_VARIABLE_DATA_KEYS]
                            [--average_embd AVERAGE_EMBD]
                            [--train_dtype {float16,float32,float64}]
                            [--use_amp USE_AMP]
                            [--no_forward_run NO_FORWARD_RUN]
                            [--sort_in_batch {descending,ascending}]
                            [--sort_batch {descending,ascending}]
                            [--drop_last_iter DROP_LAST_ITER]
                            [--spk_train_config SPK_TRAIN_CONFIG]
                            [--spk_model_file SPK_MODEL_FILE]
                            [--model_tag MODEL_TAG]
                            [--dist_backend DIST_BACKEND]
                            [--dist_init_method DIST_INIT_METHOD]
                            [--dist_world_size DIST_WORLD_SIZE]
                            [--dist_rank DIST_RANK] [--local_rank LOCAL_RANK]
                            [--dist_master_addr DIST_MASTER_ADDR]
                            [--dist_master_port DIST_MASTER_PORT]
                            [--dist_launcher {slurm,mpi,None}]
                            [--multiprocessing_distributed MULTIPROCESSING_DISTRIBUTED]
                            [--unused_parameters UNUSED_PARAMETERS]
                            [--sharded_ddp SHARDED_DDP]
                            [--use_matplotlib USE_MATPLOTLIB]
                            [--use_tensorboard USE_TENSORBOARD]
                            [--create_graph_in_tensorboard CREATE_GRAPH_IN_TENSORBOARD]
                            [--use_wandb USE_WANDB]
                            [--wandb_project WANDB_PROJECT]
                            [--wandb_id WANDB_ID]
                            [--wandb_entity WANDB_ENTITY]
                            [--wandb_name WANDB_NAME]
                            [--wandb_model_log_interval WANDB_MODEL_LOG_INTERVAL]
                            [--detect_anomaly DETECT_ANOMALY]
                            [--use_lora USE_LORA]
                            [--save_lora_only SAVE_LORA_ONLY]
                            [--lora_conf LORA_CONF]
                            [--cudnn_enabled CUDNN_ENABLED]
                            [--cudnn_benchmark CUDNN_BENCHMARK]
                            [--cudnn_deterministic CUDNN_DETERMINISTIC]
                            [--valid_batch_size VALID_BATCH_SIZE]
                            [--target_duration TARGET_DURATION]
                            [--num_eval NUM_EVAL] [--fold_length FOLD_LENGTH]
                            [--use_preprocessor USE_PREPROCESSOR]