update

speech_asr

2023-04-20 3e77fd44304a67a2b2253b4e56fede9762bb8464

 funasr/bin/train.py

@@ -1,10 +1,24 @@
import argparse
import logging
import os
import sys
from io import BytesIO

import torch

from funasr.torch_utils.model_summary import model_summary
from funasr.torch_utils.pytorch_version import pytorch_cudnn_version
from funasr.torch_utils.set_all_random_seed import set_all_random_seed
from funasr.utils import config_argparse
from funasr.utils.build_args import build_args
from funasr.utils.build_dataloader import build_dataloader
from funasr.utils.build_distributed import build_distributed
from funasr.utils.build_model import build_model
from funasr.utils.build_optimizer import build_optimizer
from funasr.utils.build_scheduler import build_scheduler
from funasr.utils.prepare_data import prepare_data
from funasr.utils.types import str2bool
from funasr.utils.yaml_no_alias_safe_dump import yaml_no_alias_safe_dump


def get_parser():
@@ -21,6 +35,7 @@
        help="The number of gpus. 0 indicates CPU mode",
    )
    parser.add_argument("--seed", type=int, default=0, help="Random seed")
    parser.add_argument("--task_name", type=str, default="asr", help="Name for different tasks")

    # ddp related
    parser.add_argument(
@@ -259,6 +274,12 @@
        action="append",
        default=[],
    )
    parser.add_argument(
        "--use_preprocessor",
        type=str2bool,
        default=True,
        help="Apply preprocessing to data or not",
    )

    # pai related
    parser.add_argument(
@@ -317,10 +338,58 @@
if __name__ == '__main__':
    parser = get_parser()
    args = parser.parse_args()
    task_args = build_args(args)
    args = argparse.Namespace(**vars(args), **vars(task_args))

    # set random seed
    set_all_random_seed(args.seed)
    torch.backends.cudnn.enabled = args.cudnn_enabled
    torch.backends.cudnn.benchmark = args.cudnn_benchmark
    torch.backends.cudnn.deterministic = args.cudnn_deterministic

    # ddp init
    args.distributed = args.dist_world_size > 1
    distributed_option = build_distributed(args)

    #
    # for logging
    if not distributed_option.distributed or distributed_option.dist_rank == 0:
        logging.basicConfig(
            level="INFO",
            format=f"[{os.uname()[1].split('.')[0]}]"
                   f" %(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
        )
    else:
        logging.basicConfig(
            level="ERROR",
            format=f"[{os.uname()[1].split('.')[0]}]"
                   f" %(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
        )

    # prepare files for dataloader
    prepare_data(args, distributed_option)

    model = build_model(args)
    optimizer = build_optimizer(args, model=model)
    scheduler = build_scheduler(args, optimizer)

    logging.info("world size: {}, rank: {}, local_rank: {}".format(distributed_option.dist_world_size,
                                                                   distributed_option.dist_rank,
                                                                   distributed_option.local_rank))
    logging.info(pytorch_cudnn_version())
    logging.info(model_summary(model))
    logging.info("Optimizer: {}".format(optimizer))
    logging.info("Scheduler: {}".format(scheduler))

    # dump args to config.yaml
    if not distributed_option.distributed or distributed_option.dist_rank == 0:
        os.makedirs(args.output_dir, exist_ok=True)
        with open(os.path.join(args.output_dir, "config.yaml"), "w") as f:
            logging.info("Saving the configuration in {}/{}".format(args.output_dir, "config.yaml"))
            if args.use_pai:
                buffer = BytesIO()
                torch.save({"config": vars(args)}, buffer)
                args.oss_bucket.put_object(os.path.join(args.output_dir, "config.dict"), buffer.getvalue())
            else:
                yaml_no_alias_safe_dump(vars(args), f, indent=4, sort_keys=False)

    train_dataloader, valid_dataloader = build_dataloader(args)