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

jmwang66

2023-06-20 2ff405b2f4ab899eff9bece232969fbb0c8f0555

 funasr/bin/asr_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)

@@ -7,77 +7,45 @@
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

#!/usr/bin/env python3
import argparse
import logging
import sys
import time
import copy
import os
import codecs
import tempfile
import requests
from pathlib import Path
from typing import Dict
from typing import List
from typing import Optional
from typing import Sequence
from typing import Tuple
from typing import Union
from typing import Dict
from typing import Any
from typing import List
import yaml

import numpy as np
import torch
import torchaudio
import yaml
from typeguard import check_argument_types
from typeguard import check_return_type
from funasr.fileio.datadir_writer import DatadirWriter
from funasr.modules.beam_search.beam_search import BeamSearch
# from funasr.modules.beam_search.beam_search import BeamSearchPara as BeamSearch

from funasr.bin.asr_infer import Speech2Text
from funasr.bin.asr_infer import Speech2TextMFCCA
from funasr.bin.asr_infer import Speech2TextParaformer, Speech2TextParaformerOnline
from funasr.bin.asr_infer import Speech2TextSAASR
from funasr.bin.asr_infer import Speech2TextTransducer
from funasr.bin.asr_infer import Speech2TextUniASR
from funasr.bin.punc_infer import Text2Punc
from funasr.bin.tp_infer import Speech2Timestamp
from funasr.bin.vad_infer import Speech2VadSegment
from funasr.build_utils.build_streaming_iterator import build_streaming_iterator
from funasr.fileio.datadir_writer import DatadirWriter
from funasr.modules.beam_search.beam_search import Hypothesis
from funasr.modules.scorers.ctc import CTCPrefixScorer
from funasr.modules.scorers.length_bonus import LengthBonus
from funasr.modules.subsampling import TooShortUttError
from funasr.tasks.asr import ASRTask
from funasr.tasks.lm import LMTask
from funasr.text.build_tokenizer import build_tokenizer
from funasr.text.token_id_converter import TokenIDConverter
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 asr_utils, postprocess_utils
from funasr.utils import config_argparse
from funasr.utils.cli_utils import get_commandline_args
from funasr.utils.timestamp_tools import time_stamp_sentence, 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.utils import asr_utils, wav_utils, postprocess_utils
from funasr.models.frontend.wav_frontend import WavFrontend, WavFrontendOnline
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
from funasr.models.e2e_asr_contextual_paraformer import NeatContextualParaformer
from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard


from funasr.utils.vad_utils import slice_padding_fbank
from funasr.tasks.vad import VADTask
from funasr.utils.timestamp_tools import time_stamp_sentence, ts_prediction_lfr6_standard
from funasr.bin.asr_infer import Speech2Text
from funasr.bin.asr_infer import Speech2TextParaformer, Speech2TextParaformerOnline
from funasr.bin.asr_infer import Speech2TextUniASR
from funasr.bin.asr_infer import Speech2TextMFCCA
from funasr.bin.vad_infer import Speech2VadSegment
from funasr.bin.punc_infer import Text2Punc
from funasr.bin.tp_infer import Speech2Timestamp
from funasr.bin.asr_infer import Speech2TextTransducer
from funasr.bin.asr_infer import Speech2TextSAASR


def inference_asr(
    maxlenratio: float,
@@ -173,18 +141,16 @@
            if isinstance(raw_inputs, torch.Tensor):
                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=speech2text.asr_train_args,
            data_path_and_name_and_type=data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            mc=mc,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
            preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
            collate_fn=ASRTask.build_collate_fn(speech2text.asr_train_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        
        finish_count = 0
@@ -360,17 +326,15 @@
            if isinstance(raw_inputs, torch.Tensor):
                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=speech2text.asr_train_args,
            data_path_and_name_and_type=data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
            preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
            collate_fn=ASRTask.build_collate_fn(speech2text.asr_train_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        
        if param_dict is not None:
@@ -611,17 +575,15 @@
            if isinstance(raw_inputs, torch.Tensor):
                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=None,
            data_path_and_name_and_type=data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=1,
            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,
        )
        
        if param_dict is not None:
@@ -657,6 +619,7 @@
            data_with_index = [(vadsegments[i], i) for i in range(n)]
            sorted_data = sorted(data_with_index, key=lambda x: x[0][1] - x[0][0])
            results_sorted = []
            
            batch_size_token_ms = batch_size_token*60
            if speech2text.device == "cpu":
                batch_size_token_ms = 0
@@ -666,7 +629,8 @@
            beg_idx = 0
            for j, _ in enumerate(range(0, n)):
                batch_size_token_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0])
                if j < n-1 and (batch_size_token_ms_cum + sorted_data[j+1][0][1] - sorted_data[j+1][0][0])<batch_size_token_ms:
                if j < n - 1 and (batch_size_token_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][
                    0]) < batch_size_token_ms:
                    continue
                batch_size_token_ms_cum = 0
                end_idx = j + 1
@@ -752,6 +716,7 @@
        return asr_result_list
    
    return _forward


def inference_paraformer_online(
        maxlenratio: float,
@@ -875,7 +840,8 @@
            feats_dims = config["frontend_conf"]["n_mels"] * config["frontend_conf"]["lfr_m"]
            cache_en = {"start_idx": 0, "cif_hidden": torch.zeros((batch_size, 1, enc_output_size)),
                        "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size, "last_chunk": False,
                        "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)), "tail_chunk": False}
                        "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)),
                        "tail_chunk": False}
            cache["encoder"] = cache_en

            cache_de = {"decode_fsmn": None}
@@ -1059,17 +1025,15 @@
            if isinstance(raw_inputs, torch.Tensor):
                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=speech2text.asr_train_args,
            data_path_and_name_and_type=data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
            preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
            collate_fn=ASRTask.build_collate_fn(speech2text.asr_train_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        
        finish_count = 0
@@ -1214,18 +1178,16 @@
            if isinstance(raw_inputs, torch.Tensor):
                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=speech2text.asr_train_args,
            data_path_and_name_and_type=data_path_and_name_and_type,
            dtype=dtype,
            batch_size=batch_size,
            fs=fs,
            mc=True,
            key_file=key_file,
            num_workers=num_workers,
            preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
            collate_fn=ASRTask.build_collate_fn(speech2text.asr_train_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        
        finish_count = 0
@@ -1277,6 +1239,7 @@
        return asr_result_list
    
    return _forward


def inference_transducer(
    output_dir: str,
@@ -1400,20 +1363,14 @@
                 **kwargs,
                 ):
        # 3. Build data-iterator
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
        loader = build_streaming_iterator(
            task_name="asr",
            preprocess_args=speech2text.asr_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=ASRTask.build_preprocess_fn(
                speech2text.asr_train_args, False
            ),
            collate_fn=ASRTask.build_collate_fn(
                speech2text.asr_train_args, False
            ),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
    
        # 4 .Start for-loop
@@ -1464,7 +1421,6 @@
    
                    if text is not None:
                        ibest_writer["text"][key] = text


    return _forward

@@ -1561,18 +1517,16 @@
            if isinstance(raw_inputs, torch.Tensor):
                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=speech2text.asr_train_args,
            data_path_and_name_and_type=data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            mc=mc,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
            preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
            collate_fn=ASRTask.build_collate_fn(speech2text.asr_train_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        
        finish_count = 0
@@ -1922,7 +1876,6 @@

    inference_pipeline = inference_launch(**kwargs)
    return inference_pipeline(kwargs["data_path_and_name_and_type"], hotword=kwargs.get("hotword", None))



if __name__ == "__main__":