mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
263 lines
7.8 KiB
Python
263 lines
7.8 KiB
Python
#!/usr/bin/env python3
|
|
# -*- encoding: utf-8 -*-
|
|
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
|
|
# MIT License (https://opensource.org/licenses/MIT)
|
|
|
|
import sys
|
|
|
|
from funasr.utils.types import str2bool
|
|
from funasr.utils.types import str2triple_str
|
|
from funasr.utils.types import str_or_none
|
|
from funasr.utils import config_argparse
|
|
import argparse
|
|
|
|
|
|
def get_parser():
|
|
parser = config_argparse.ArgumentParser(
|
|
description="ASR Decoding",
|
|
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
|
|
)
|
|
|
|
# Note(kamo): Use '_' instead of '-' as separator.
|
|
# '-' is confusing if written in yaml.
|
|
parser.add_argument(
|
|
"--log_level",
|
|
type=lambda x: x.upper(),
|
|
default="INFO",
|
|
choices=("CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG", "NOTSET"),
|
|
help="The verbose level of logging",
|
|
)
|
|
|
|
parser.add_argument("--output_dir", type=str, default=None)
|
|
parser.add_argument(
|
|
"--ngpu",
|
|
type=int,
|
|
default=1,
|
|
help="The number of gpus. 0 indicates CPU mode",
|
|
)
|
|
parser.add_argument(
|
|
"--njob",
|
|
type=int,
|
|
default=1,
|
|
help="The number of jobs for each gpu",
|
|
)
|
|
parser.add_argument(
|
|
"--gpuid_list",
|
|
type=str,
|
|
default="",
|
|
help="The visible gpus",
|
|
)
|
|
parser.add_argument("--seed", type=int, default=0, help="Random seed")
|
|
parser.add_argument(
|
|
"--dtype",
|
|
default="float32",
|
|
choices=["float16", "float32", "float64"],
|
|
help="Data type",
|
|
)
|
|
parser.add_argument(
|
|
"--num_workers",
|
|
type=int,
|
|
default=1,
|
|
help="The number of workers used for DataLoader",
|
|
)
|
|
|
|
group = parser.add_argument_group("Input data related")
|
|
group.add_argument(
|
|
"--data_path_and_name_and_type",
|
|
type=str2triple_str,
|
|
required=False,
|
|
action="append",
|
|
)
|
|
group.add_argument("--key_file", type=str_or_none)
|
|
parser.add_argument(
|
|
"--hotword",
|
|
type=str_or_none,
|
|
default=None,
|
|
help="hotword file path or hotwords seperated by space"
|
|
)
|
|
group.add_argument("--allow_variable_data_keys", type=str2bool, default=False)
|
|
group.add_argument(
|
|
"--mc",
|
|
type=bool,
|
|
default=False,
|
|
help="MultiChannel input",
|
|
)
|
|
|
|
group = parser.add_argument_group("The model configuration related")
|
|
group.add_argument(
|
|
"--vad_infer_config",
|
|
type=str,
|
|
help="VAD infer configuration",
|
|
)
|
|
group.add_argument(
|
|
"--vad_model_file",
|
|
type=str,
|
|
help="VAD model parameter file",
|
|
)
|
|
group.add_argument(
|
|
"--punc_infer_config",
|
|
type=str,
|
|
help="PUNC infer configuration",
|
|
)
|
|
group.add_argument(
|
|
"--punc_model_file",
|
|
type=str,
|
|
help="PUNC model parameter file",
|
|
)
|
|
group.add_argument(
|
|
"--cmvn_file",
|
|
type=str,
|
|
help="Global CMVN file",
|
|
)
|
|
group.add_argument(
|
|
"--asr_train_config",
|
|
type=str,
|
|
help="ASR training configuration",
|
|
)
|
|
group.add_argument(
|
|
"--asr_model_file",
|
|
type=str,
|
|
help="ASR model parameter file",
|
|
)
|
|
group.add_argument(
|
|
"--sv_model_file",
|
|
type=str,
|
|
help="SV model parameter file",
|
|
)
|
|
group.add_argument(
|
|
"--lm_train_config",
|
|
type=str,
|
|
help="LM training configuration",
|
|
)
|
|
group.add_argument(
|
|
"--lm_file",
|
|
type=str,
|
|
help="LM parameter file",
|
|
)
|
|
group.add_argument(
|
|
"--word_lm_train_config",
|
|
type=str,
|
|
help="Word LM training configuration",
|
|
)
|
|
group.add_argument(
|
|
"--word_lm_file",
|
|
type=str,
|
|
help="Word LM parameter file",
|
|
)
|
|
group.add_argument(
|
|
"--ngram_file",
|
|
type=str,
|
|
help="N-gram parameter file",
|
|
)
|
|
group.add_argument(
|
|
"--model_tag",
|
|
type=str,
|
|
help="Pretrained model tag. If specify this option, *_train_config and "
|
|
"*_file will be overwritten",
|
|
)
|
|
group.add_argument(
|
|
"--beam_search_config",
|
|
default={},
|
|
help="The keyword arguments for transducer beam search.",
|
|
)
|
|
|
|
group = parser.add_argument_group("Beam-search related")
|
|
group.add_argument(
|
|
"--batch_size",
|
|
type=int,
|
|
default=1,
|
|
help="The batch size for inference",
|
|
)
|
|
group.add_argument("--nbest", type=int, default=5, help="Output N-best hypotheses")
|
|
group.add_argument("--beam_size", type=int, default=20, help="Beam size")
|
|
group.add_argument("--penalty", type=float, default=0.0, help="Insertion penalty")
|
|
group.add_argument(
|
|
"--maxlenratio",
|
|
type=float,
|
|
default=0.0,
|
|
help="Input length ratio to obtain max output length. "
|
|
"If maxlenratio=0.0 (default), it uses a end-detect "
|
|
"function "
|
|
"to automatically find maximum hypothesis lengths."
|
|
"If maxlenratio<0.0, its absolute value is interpreted"
|
|
"as a constant max output length",
|
|
)
|
|
group.add_argument(
|
|
"--minlenratio",
|
|
type=float,
|
|
default=0.0,
|
|
help="Input length ratio to obtain min output length",
|
|
)
|
|
group.add_argument(
|
|
"--ctc_weight",
|
|
type=float,
|
|
default=0.0,
|
|
help="CTC weight in joint decoding",
|
|
)
|
|
group.add_argument("--lm_weight", type=float, default=1.0, help="RNNLM weight")
|
|
group.add_argument("--ngram_weight", type=float, default=0.9, help="ngram weight")
|
|
group.add_argument("--streaming", type=str2bool, default=False)
|
|
group.add_argument("--fake_streaming", type=str2bool, default=False)
|
|
group.add_argument("--full_utt", type=str2bool, default=False)
|
|
group.add_argument("--chunk_size", type=int, default=16)
|
|
group.add_argument("--left_context", type=int, default=16)
|
|
group.add_argument("--right_context", type=int, default=0)
|
|
group.add_argument(
|
|
"--display_partial_hypotheses",
|
|
type=bool,
|
|
default=False,
|
|
help="Whether to display partial hypotheses during chunk-by-chunk inference.",
|
|
)
|
|
|
|
group = parser.add_argument_group("Dynamic quantization related")
|
|
group.add_argument(
|
|
"--quantize_asr_model",
|
|
type=bool,
|
|
default=False,
|
|
help="Apply dynamic quantization to ASR model.",
|
|
)
|
|
group.add_argument(
|
|
"--quantize_modules",
|
|
nargs="*",
|
|
default=None,
|
|
help="""Module names to apply dynamic quantization on.
|
|
The module names are provided as a list, where each name is separated
|
|
by a comma (e.g.: --quantize-config=[Linear,LSTM,GRU]).
|
|
Each specified name should be an attribute of 'torch.nn', e.g.:
|
|
torch.nn.Linear, torch.nn.LSTM, torch.nn.GRU, ...""",
|
|
)
|
|
group.add_argument(
|
|
"--quantize_dtype",
|
|
type=str,
|
|
default="qint8",
|
|
choices=["float16", "qint8"],
|
|
help="Dtype for dynamic quantization.",
|
|
)
|
|
|
|
group = parser.add_argument_group("Text converter related")
|
|
group.add_argument(
|
|
"--token_type",
|
|
type=str_or_none,
|
|
default=None,
|
|
choices=["char", "bpe", None],
|
|
help="The token type for ASR model. "
|
|
"If not given, refers from the training args",
|
|
)
|
|
group.add_argument(
|
|
"--bpemodel",
|
|
type=str_or_none,
|
|
default=None,
|
|
help="The model path of sentencepiece. "
|
|
"If not given, refers from the training args",
|
|
)
|
|
group.add_argument("--token_num_relax", type=int, default=1, help="")
|
|
group.add_argument("--decoding_ind", type=int, default=0, help="")
|
|
group.add_argument("--decoding_mode", type=str, default="model1", help="")
|
|
group.add_argument(
|
|
"--ctc_weight2",
|
|
type=float,
|
|
default=0.0,
|
|
help="CTC weight in joint decoding",
|
|
)
|
|
return parser
|