You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/deepspeech/training/cli.py

70 lines
2.8 KiB

Support paddle 2.x (#538) * 2.x model * model test pass * fix data * fix soundfile with flac support * one thread dataloader test pass * export feasture size add trainer and utils add setup model and dataloader update travis using Bionic dist * add venv; test under venv * fix unittest; train and valid * add train and config * add config and train script * fix ctc cuda memcopy error * fix imports * fix train valid log * fix dataset batch shuffle shift start from 1 fix rank_zero_only decreator error close tensorboard when train over add decoding config and code * test process can run * test with decoding * test and infer with decoding * fix infer * fix ctc loss lr schedule sortagrad logger * aishell egs * refactor train add aishell egs * fix dataset batch shuffle and add batch sampler log print model parameter * fix model and ctc * sequence_mask make all inputs zeros, which cause grad be zero, this is a bug of LessThanOp add grad clip by global norm add model train test notebook * ctc loss remove run prefix using ord value as text id * using unk when training compute_loss need text ids ord id using in test mode, which compute wer/cer * fix tester * add lr_deacy refactor code * fix tools * fix ci add tune fix gru model bugs add dataset and model test * fix decoding * refactor repo fix decoding * fix musan and rir dataset * refactor io, loss, conv, rnn, gradclip, model, utils * fix ci and import * refactor model add export jit model * add deploy bin and test it * rm uselss egs * add layer tools * refactor socket server new model from pretrain * remve useless * fix instability loss and grad nan or inf for librispeech training * fix sampler * fix libri train.sh * fix doc * add license on cpp * fix doc * fix libri script * fix install * clip 5 wer 7.39, clip 400 wer 7.54, 1.8 clip 400 baseline 7.49
4 years ago
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import argparse
def default_argument_parser():
r"""A simple yet genral argument parser for experiments with parakeet.
This is used in examples with parakeet. And it is intended to be used by
other experiments with parakeet. It requires a minimal set of command line
arguments to start a training script.
The ``--config`` and ``--opts`` are used for overwrite the deault
configuration.
The ``--data`` and ``--output`` specifies the data path and output path.
Resuming training from existing progress at the output directory is the
intended default behavior.
The ``--checkpoint_path`` specifies the checkpoint to load from.
The ``--device`` and ``--nprocs`` specifies how to run the training.
See Also
--------
parakeet.training.experiment
Returns
-------
argparse.ArgumentParser
the parser
"""
parser = argparse.ArgumentParser()
# yapf: disable
# data and output
parser.add_argument("--config", metavar="FILE", help="path of the config file to overwrite to default config with.")
parser.add_argument("--dump-config", metavar="FILE", help="dump config to yaml file.")
# parser.add_argument("--data", metavar="DATA_DIR", help="path to the datatset.")
parser.add_argument("--output", metavar="OUTPUT_DIR", help="path to save checkpoint and logs.")
# load from saved checkpoint
parser.add_argument("--checkpoint_path", type=str, help="path of the checkpoint to load")
# save jit model to
parser.add_argument("--export_path", type=str, help="path of the jit model to save")
# running
parser.add_argument("--device", type=str, default='gpu', choices=["cpu", "gpu"], help="device type to use, cpu and gpu are supported.")
parser.add_argument("--nprocs", type=int, default=1, help="number of parallel processes to use.")
# overwrite extra config and default config
#parser.add_argument("--opts", nargs=argparse.REMAINDER, help="options to overwrite --config file and the default config, passing in KEY VALUE pairs")
parser.add_argument("--opts", type=str, default=[], nargs='+', help="options to overwrite --config file and the default config, passing in KEY VALUE pairs")
# yapd: enable
return parser