From 49c00a7d6cb9c05d4bd0bb0fc8b59a2eed4b8950 Mon Sep 17 00:00:00 2001
From: huangmingming <huangmingming@deepscience.cn>
Date: 星期一, 13 三月 2023 12:07:11 +0800
Subject: [PATCH] grpc client remove VAD
---
funasr/bin/tp_inference.py | 52 +++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 39 insertions(+), 13 deletions(-)
diff --git a/funasr/bin/tp_inference.py b/funasr/bin/tp_inference.py
index 67e82a7..e7a1f1b 100644
--- a/funasr/bin/tp_inference.py
+++ b/funasr/bin/tp_inference.py
@@ -1,5 +1,6 @@
import argparse
import logging
+from optparse import Option
import sys
import json
from pathlib import Path
@@ -11,15 +12,12 @@
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.fileio.datadir_writer import DatadirWriter
-from funasr.modules.scorers.scorer_interface import BatchScorerInterface
-from funasr.modules.subsampling import TooShortUttError
+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.torch_utils.set_all_random_seed import set_all_random_seed
@@ -28,7 +26,6 @@
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
from funasr.text.token_id_converter import TokenIDConverter
@@ -91,7 +88,7 @@
for char, timestamp in zip(new_char_list, timestamp_list):
res_str += "{} {} {};".format(char, str(timestamp[0]+0.0005)[:5], str(timestamp[1]+0.0005)[:5])
res = []
- for char, timestamp in zip(char_list, timestamp_list):
+ for char, timestamp in zip(new_char_list, timestamp_list):
if char != '<sil>':
res.append([int(timestamp[0] * 1000), int(timestamp[1] * 1000)])
return res_str, res
@@ -113,8 +110,8 @@
timestamp_infer_config, timestamp_model_file, device
)
if 'cuda' in device:
- tp_model = tp_model.cuda()
-
+ tp_model = tp_model.cuda() # force model to cuda
+
frontend = None
if tp_train_args.frontend is not None:
frontend = WavFrontend(cmvn_file=timestamp_cmvn_file, **tp_train_args.frontend_conf)
@@ -191,6 +188,8 @@
dtype: str = "float32",
seed: int = 0,
num_workers: int = 1,
+ split_with_space: bool = True,
+ seg_dict_file: Optional[str] = None,
**kwargs,
):
inference_pipeline = inference_modelscope(
@@ -206,6 +205,8 @@
dtype=dtype,
seed=seed,
num_workers=num_workers,
+ split_with_space=split_with_space,
+ seg_dict_file=seg_dict_file,
**kwargs,
)
return inference_pipeline(data_path_and_name_and_type, raw_inputs)
@@ -226,6 +227,8 @@
dtype: str = "float32",
seed: int = 0,
num_workers: int = 1,
+ split_with_space: bool = True,
+ seg_dict_file: Optional[str] = None,
**kwargs,
):
assert check_argument_types()
@@ -256,6 +259,19 @@
)
logging.info("speechtext2timestamp_kwargs: {}".format(speechtext2timestamp_kwargs))
speechtext2timestamp = SpeechText2Timestamp(**speechtext2timestamp_kwargs)
+
+ preprocessor = LMPreprocessor(
+ train=False,
+ token_type=speechtext2timestamp.tp_train_args.token_type,
+ token_list=speechtext2timestamp.tp_train_args.token_list,
+ bpemodel=None,
+ text_cleaner=None,
+ g2p_type=None,
+ text_name="text",
+ non_linguistic_symbols=speechtext2timestamp.tp_train_args.non_linguistic_symbols,
+ split_with_space=split_with_space,
+ seg_dict_file=seg_dict_file,
+ )
def _forward(
data_path_and_name_and_type,
@@ -277,14 +293,11 @@
batch_size=batch_size,
key_file=key_file,
num_workers=num_workers,
- preprocess_fn=ASRTask.build_preprocess_fn(speechtext2timestamp.tp_train_args, False),
+ preprocess_fn=preprocessor,
collate_fn=ASRTask.build_collate_fn(speechtext2timestamp.tp_train_args, False),
allow_variable_data_keys=allow_variable_data_keys,
inference=True,
)
-
- finish_count = 0
- file_count = 1
tp_result_list = []
for keys, batch in loader:
@@ -304,7 +317,8 @@
token = speechtext2timestamp.converter.ids2tokens(batch['text'][batch_id])
ts_str, ts_list = time_stamp_lfr6_advance(us_alphas[batch_id], us_cif_peak[batch_id], token)
logging.warning(ts_str)
- tp_result_list.append({'text':"".join([i for i in token if i != '<sil>']), 'timestamp': ts_list})
+ item = {'key': key, 'value': ts_str, 'timestamp':ts_list}
+ tp_result_list.append(item)
return tp_result_list
return _forward
@@ -389,6 +403,18 @@
default=1,
help="The batch size for inference",
)
+ group.add_argument(
+ "--seg_dict_file",
+ type=str,
+ default=None,
+ help="The batch size for inference",
+ )
+ group.add_argument(
+ "--split_with_space",
+ type=bool,
+ default=False,
+ help="The batch size for inference",
+ )
return parser
--
Gitblit v1.9.1