Merge pull request #653 from alibaba-damo-academy/dev_wjm_infer

jmwang66

2023-06-20 2ff405b2f4ab899eff9bece232969fbb0c8f0555

 funasr/bin/tp_inference_launch.py

@@ -1,5 +1,5 @@
# -*- encoding: utf-8 -*-
#!/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)

@@ -8,46 +8,25 @@
import logging
import os
import sys
from typing import Union, Dict, Any

from funasr.utils import config_argparse
from funasr.utils.cli_utils import get_commandline_args
from funasr.utils.types import str2bool
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none

import argparse
import logging
from optparse import Option
import sys
import json
from pathlib import Path
from typing import Any
from typing import List
from typing import Optional
from typing import Sequence
from typing import Tuple
from typing import Union
from typing import Dict

import numpy as np
import torch
from typeguard import check_argument_types

from funasr.fileio.datadir_writer import DatadirWriter
from funasr.bin.tp_infer import Speech2Timestamp
from funasr.build_utils.build_streaming_iterator import build_streaming_iterator
from funasr.datasets.preprocessor import LMPreprocessor
from funasr.tasks.asr import ASRTaskAligner as ASRTask
from funasr.torch_utils.device_funcs import to_device
from funasr.fileio.datadir_writer import DatadirWriter
from funasr.torch_utils.set_all_random_seed import set_all_random_seed
from funasr.utils import config_argparse
from funasr.utils.cli_utils import get_commandline_args
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
from funasr.utils.types import str2bool
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.text.token_id_converter import TokenIDConverter
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
from funasr.bin.tp_infer import Speech2Timestamp


def inference_tp(
    batch_size: int,
@@ -141,16 +120,15 @@
                raw_inputs = raw_inputs.numpy()
            data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
        
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
        loader = build_streaming_iterator(
            task_name="asr",
            preprocess_args=speechtext2timestamp.tp_train_args,
            data_path_and_name_and_type=data_path_and_name_and_type,
            dtype=dtype,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
            preprocess_fn=preprocessor,
            collate_fn=ASRTask.build_collate_fn(speechtext2timestamp.tp_train_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        
        tp_result_list = []
@@ -182,14 +160,13 @@
    return _forward




def inference_launch(mode, **kwargs):
    if mode == "tp_norm":
        return inference_tp(**kwargs)
    else:
        logging.info("Unknown decoding mode: {}".format(mode))
        return None


def get_parser():
    parser = config_argparse.ArgumentParser(
@@ -306,7 +283,6 @@

    inference_pipeline = inference_launch(**kwargs)
    return inference_pipeline(kwargs["data_path_and_name_and_type"])



if __name__ == "__main__":