readme

游雁

2023-03-13 fc08b62d05723cdc1ce021bb8ba044ca014fb1f7

 funasr/tasks/abs_task.py

@@ -43,12 +43,15 @@
from funasr.iterators.chunk_iter_factory import ChunkIterFactory
from funasr.iterators.multiple_iter_factory import MultipleIterFactory
from funasr.iterators.sequence_iter_factory import SequenceIterFactory
from funasr.main_funcs.collect_stats import collect_stats
from funasr.optimizers.sgd import SGD
from funasr.optimizers.fairseq_adam import FairseqAdam
from funasr.samplers.build_batch_sampler import BATCH_TYPES
from funasr.samplers.build_batch_sampler import build_batch_sampler
from funasr.samplers.unsorted_batch_sampler import UnsortedBatchSampler
from funasr.schedulers.noam_lr import NoamLR
from funasr.schedulers.warmup_lr import WarmupLR
from funasr.schedulers.tri_stage_scheduler import TriStageLR
from funasr.torch_utils.load_pretrained_model import load_pretrained_model
from funasr.torch_utils.model_summary import model_summary
from funasr.torch_utils.pytorch_version import pytorch_cudnn_version
@@ -83,6 +86,7 @@

optim_classes = dict(
    adam=torch.optim.Adam,
    fairseq_adam=FairseqAdam,
    adamw=torch.optim.AdamW,
    sgd=SGD,
    adadelta=torch.optim.Adadelta,
@@ -149,6 +153,7 @@
    CosineAnnealingLR=torch.optim.lr_scheduler.CosineAnnealingLR,
    noamlr=NoamLR,
    warmuplr=WarmupLR,
    tri_stage=TriStageLR,
    cycliclr=torch.optim.lr_scheduler.CyclicLR,
    onecyclelr=torch.optim.lr_scheduler.OneCycleLR,
    CosineAnnealingWarmRestarts=torch.optim.lr_scheduler.CosineAnnealingWarmRestarts,
@@ -1276,6 +1281,52 @@

        if args.dry_run:
            pass
        elif args.collect_stats:
            # Perform on collect_stats mode. This mode has two roles
            # - Derive the length and dimension of all input data
            # - Accumulate feats, square values, and the length for whitening

            if args.valid_batch_size is None:
                args.valid_batch_size = args.batch_size

            if len(args.train_shape_file) != 0:
                train_key_file = args.train_shape_file[0]
            else:
                train_key_file = None
            if len(args.valid_shape_file) != 0:
                valid_key_file = args.valid_shape_file[0]
            else:
                valid_key_file = None

            collect_stats(
                model=model,
                train_iter=cls.build_streaming_iterator(
                    data_path_and_name_and_type=args.train_data_path_and_name_and_type,
                    key_file=train_key_file,
                    batch_size=args.batch_size,
                    dtype=args.train_dtype,
                    num_workers=args.num_workers,
                    allow_variable_data_keys=args.allow_variable_data_keys,
                    ngpu=args.ngpu,
                    preprocess_fn=cls.build_preprocess_fn(args, train=False),
                    collate_fn=cls.build_collate_fn(args, train=False),
                ),
                valid_iter=cls.build_streaming_iterator(
                    data_path_and_name_and_type=args.valid_data_path_and_name_and_type,
                    key_file=valid_key_file,
                    batch_size=args.valid_batch_size,
                    dtype=args.train_dtype,
                    num_workers=args.num_workers,
                    allow_variable_data_keys=args.allow_variable_data_keys,
                    ngpu=args.ngpu,
                    preprocess_fn=cls.build_preprocess_fn(args, train=False),
                    collate_fn=cls.build_collate_fn(args, train=False),
                ),
                output_dir=output_dir,
                ngpu=args.ngpu,
                log_interval=args.log_interval,
                write_collected_feats=args.write_collected_feats,
            )
        else:
            logging.info("Training args: {}".format(args))
            # 6. Loads pre-trained model
@@ -1297,12 +1348,16 @@
            if args.dataset_type == "large":
                from funasr.datasets.large_datasets.build_dataloader import ArkDataLoader
                train_iter_factory = ArkDataLoader(args.train_data_file, args.token_list, args.dataset_conf,
                                                   frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None,
                                                   seg_dict_file=args.seg_dict_file if hasattr(args,
                                                                                               "seg_dict_file") else None,
                                                   punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None,
                                                   mode="train")
                valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf,
                valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf, 
                                                   frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None,
                                                   seg_dict_file=args.seg_dict_file if hasattr(args,
                                                                                               "seg_dict_file") else None,
                                                   punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None,
                                                   mode="eval")
            elif args.dataset_type == "small":
                train_iter_factory = cls.build_iter_factory(
@@ -1521,6 +1576,7 @@
            preprocess=iter_options.preprocess_fn,
            max_cache_size=iter_options.max_cache_size,
            max_cache_fd=iter_options.max_cache_fd,
            dest_sample_rate=args.frontend_conf["fs"],
        )
        cls.check_task_requirements(
            dataset, args.allow_variable_data_keys, train=iter_options.train
@@ -1792,6 +1848,7 @@
            key_file: str = None,
            batch_size: int = 1,
            fs: dict = None,
            mc: bool = False,
            dtype: str = np.float32,
            num_workers: int = 1,
            allow_variable_data_keys: bool = False,
@@ -1810,6 +1867,7 @@
            data_path_and_name_and_type,
            float_dtype=dtype,
            fs=fs,
            mc=mc,
            preprocess=preprocess_fn,
            key_file=key_file,
        )