Merge pull request #687 from alibaba-damo-academy/dev_lhn

hnluo

2023-06-29 c2dee5e3c29eba79e591d9e9caebaef15ea4e56b

 funasr/bin/vad_inference_launch.py

@@ -1,58 +1,34 @@
# -*- 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)


import torch

torch.set_num_threads(1)

import argparse
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
import os
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 math
import numpy as np
import torch
from typeguard import check_argument_types
from typeguard import check_return_type

from funasr.build_utils.build_streaming_iterator import build_streaming_iterator
from funasr.fileio.datadir_writer import DatadirWriter
from funasr.modules.scorers.scorer_interface import BatchScorerInterface
from funasr.modules.subsampling import TooShortUttError
from funasr.tasks.vad import VADTask
from funasr.torch_utils.device_funcs import to_device
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.types import str2bool
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from funasr.utils import asr_utils, wav_utils, postprocess_utils
from funasr.models.frontend.wav_frontend import WavFrontend, WavFrontendOnline
from funasr.bin.vad_infer import Speech2VadSegment, Speech2VadSegmentOnline


def inference_vad(
        batch_size: int,
@@ -74,7 +50,6 @@
    assert check_argument_types()
    if batch_size > 1:
        raise NotImplementedError("batch decoding is not implemented")


    logging.basicConfig(
        level=log_level,
@@ -112,16 +87,14 @@
            if isinstance(raw_inputs, torch.Tensor):
                raw_inputs = raw_inputs.numpy()
            data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
        loader = VADTask.build_streaming_iterator(
            data_path_and_name_and_type,
        loader = build_streaming_iterator(
            task_name="vad",
            preprocess_args=None,
            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=VADTask.build_preprocess_fn(speech2vadsegment.vad_infer_args, False),
            collate_fn=VADTask.build_collate_fn(speech2vadsegment.vad_infer_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )

        finish_count = 0
@@ -157,6 +130,7 @@

    return _forward


def inference_vad_online(
        batch_size: int,
        ngpu: int,
@@ -175,7 +149,6 @@
        **kwargs,
):
    assert check_argument_types()


    logging.basicConfig(
        level=log_level,
@@ -214,16 +187,14 @@
            if isinstance(raw_inputs, torch.Tensor):
                raw_inputs = raw_inputs.numpy()
            data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
        loader = VADTask.build_streaming_iterator(
            data_path_and_name_and_type,
        loader = build_streaming_iterator(
            task_name="vad",
            preprocess_args=None,
            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=VADTask.build_preprocess_fn(speech2vadsegment.vad_infer_args, False),
            collate_fn=VADTask.build_collate_fn(speech2vadsegment.vad_infer_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )

        finish_count = 0
@@ -239,9 +210,13 @@
            ibest_writer = None

        vad_results = []
        batch_in_cache = param_dict['in_cache'] if param_dict is not None else dict()
        is_final = param_dict.get('is_final', False) if param_dict is not None else False
        max_end_sil = param_dict.get('max_end_sil', 800) if param_dict is not None else 800
        if param_dict is None:
            param_dict = dict()
            param_dict['in_cache'] = dict()
            param_dict['is_final'] = True
        batch_in_cache = param_dict.get('in_cache', dict())
        is_final = param_dict.get('is_final', False)
        max_end_sil = param_dict.get('max_end_sil', 800)
        for keys, batch in loader:
            assert isinstance(batch, dict), type(batch)
            assert all(isinstance(s, str) for s in keys), keys
@@ -269,8 +244,6 @@
    return _forward




def inference_launch(mode, **kwargs):
    if mode == "offline":
        return inference_vad(**kwargs)
@@ -279,6 +252,7 @@
    else:
        logging.info("Unknown decoding mode: {}".format(mode))
        return None


def get_parser():
    parser = config_argparse.ArgumentParser(
@@ -401,5 +375,6 @@
    inference_pipeline = inference_launch(**kwargs)
    return inference_pipeline(kwargs["data_path_and_name_and_type"])


if __name__ == "__main__":
    main()