update

shixian.shi

2023-06-27 8d519b9dc66e0df35c15110ef23a26d07bc7f7c3

 funasr/bin/asr_inference_launch.py

@@ -19,6 +19,7 @@
import numpy as np
import torch
import torchaudio
import soundfile
import yaml
from typeguard import check_argument_types

@@ -31,11 +32,10 @@
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.subsampling import TooShortUttError
from funasr.tasks.asr import ASRTask
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 asr_utils, postprocess_utils
@@ -142,18 +142,16 @@
            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
@@ -262,6 +260,7 @@
        export_mode = param_dict.get("export_mode", False)
    else:
        hotword_list_or_file = None
    clas_scale = param_dict.get('clas_scale', 1.0)

    if kwargs.get("device", None) == "cpu":
        ngpu = 0
@@ -294,6 +293,7 @@
        penalty=penalty,
        nbest=nbest,
        hotword_list_or_file=hotword_list_or_file,
        clas_sacle=clas_scale,
    )

    speech2text = Speech2TextParaformer(**speech2text_kwargs)
@@ -329,17 +329,15 @@
            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:
@@ -580,17 +578,15 @@
            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:
@@ -626,7 +622,12 @@
            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
            
            batch_size_token_ms = batch_size_token*60
            if speech2text.device == "cpu":
                batch_size_token_ms = 0
            batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
            
            batch_size_token_ms_cum = 0
            beg_idx = 0
            for j, _ in enumerate(range(0, n)):
@@ -865,7 +866,13 @@
            raw_inputs = _load_bytes(data_path_and_name_and_type[0])
            raw_inputs = torch.tensor(raw_inputs)
        if data_path_and_name_and_type is not None and data_path_and_name_and_type[2] == "sound":
            raw_inputs = torchaudio.load(data_path_and_name_and_type[0])[0][0]
            try:
                raw_inputs = torchaudio.load(data_path_and_name_and_type[0])[0][0]
            except:
                raw_inputs = soundfile.read(data_path_and_name_and_type[0], dtype='float32')[0]
                if raw_inputs.ndim == 2:
                    raw_inputs = raw_inputs[:, 0]
                raw_inputs = torch.tensor(raw_inputs)
        if data_path_and_name_and_type is None and raw_inputs is not None:
            if isinstance(raw_inputs, np.ndarray):
                raw_inputs = torch.tensor(raw_inputs)
@@ -1027,17 +1034,15 @@
            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
@@ -1182,18 +1187,16 @@
            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
@@ -1369,20 +1372,14 @@
                 **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
@@ -1529,18 +1526,16 @@
            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