From 2ff405b2f4ab899eff9bece232969fbb0c8f0555 Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 20 六月 2023 00:26:37 +0800
Subject: [PATCH] Merge pull request #653 from alibaba-damo-academy/dev_wjm_infer
---
funasr/bin/tp_inference_launch.py | 116 +++++++++++++++++++++++-----------------------------------
1 files changed, 46 insertions(+), 70 deletions(-)
diff --git a/funasr/bin/tp_inference_launch.py b/funasr/bin/tp_inference_launch.py
index a8d67ef..3f8df0c 100644
--- a/funasr/bin/tp_inference_launch.py
+++ b/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)
@@ -8,87 +8,66 @@
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,
- ngpu: int,
- log_level: Union[int, str],
- # data_path_and_name_and_type,
- timestamp_infer_config: Optional[str],
- timestamp_model_file: Optional[str],
- timestamp_cmvn_file: Optional[str] = None,
- # raw_inputs: Union[np.ndarray, torch.Tensor] = None,
- key_file: Optional[str] = None,
- allow_variable_data_keys: bool = False,
- output_dir: Optional[str] = None,
- dtype: str = "float32",
- seed: int = 0,
- num_workers: int = 1,
- split_with_space: bool = True,
- seg_dict_file: Optional[str] = None,
- **kwargs,
+ batch_size: int,
+ ngpu: int,
+ log_level: Union[int, str],
+ # data_path_and_name_and_type,
+ timestamp_infer_config: Optional[str],
+ timestamp_model_file: Optional[str],
+ timestamp_cmvn_file: Optional[str] = None,
+ # raw_inputs: Union[np.ndarray, torch.Tensor] = None,
+ key_file: Optional[str] = None,
+ allow_variable_data_keys: bool = False,
+ output_dir: Optional[str] = None,
+ 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()
ncpu = kwargs.get("ncpu", 1)
torch.set_num_threads(ncpu)
-
+
if batch_size > 1:
raise NotImplementedError("batch decoding is not implemented")
if ngpu > 1:
raise NotImplementedError("only single GPU decoding is supported")
-
+
logging.basicConfig(
level=log_level,
format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
)
-
+
if ngpu >= 1 and torch.cuda.is_available():
device = "cuda"
else:
device = "cpu"
# 1. Set random-seed
set_all_random_seed(seed)
-
+
# 2. Build speech2vadsegment
speechtext2timestamp_kwargs = dict(
timestamp_infer_config=timestamp_infer_config,
@@ -99,7 +78,7 @@
)
logging.info("speechtext2timestamp_kwargs: {}".format(speechtext2timestamp_kwargs))
speechtext2timestamp = Speech2Timestamp(**speechtext2timestamp_kwargs)
-
+
preprocessor = LMPreprocessor(
train=False,
token_type=speechtext2timestamp.tp_train_args.token_type,
@@ -112,21 +91,21 @@
split_with_space=split_with_space,
seg_dict_file=seg_dict_file,
)
-
+
if output_dir is not None:
writer = DatadirWriter(output_dir)
tp_writer = writer[f"timestamp_prediction"]
# ibest_writer["token_list"][""] = " ".join(speech2text.asr_train_args.token_list)
else:
tp_writer = None
-
+
def _forward(
- data_path_and_name_and_type,
- raw_inputs: Union[np.ndarray, torch.Tensor] = None,
- output_dir_v2: Optional[str] = None,
- fs: dict = None,
- param_dict: dict = None,
- **kwargs
+ data_path_and_name_and_type,
+ raw_inputs: Union[np.ndarray, torch.Tensor] = None,
+ output_dir_v2: Optional[str] = None,
+ fs: dict = None,
+ param_dict: dict = None,
+ **kwargs
):
output_path = output_dir_v2 if output_dir_v2 is not None else output_dir
writer = None
@@ -140,32 +119,31 @@
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=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 = []
for keys, batch in loader:
assert isinstance(batch, dict), type(batch)
assert all(isinstance(s, str) for s in keys), keys
_bs = len(next(iter(batch.values())))
assert len(keys) == _bs, f"{len(keys)} != {_bs}"
-
+
logging.info("timestamp predicting, utt_id: {}".format(keys))
_batch = {'speech': batch['speech'],
'speech_lengths': batch['speech_lengths'],
'text_lengths': batch['text_lengths']}
us_alphas, us_cif_peak = speechtext2timestamp(**_batch)
-
+
for batch_id in range(_bs):
key = keys[batch_id]
token = speechtext2timestamp.converter.ids2tokens(batch['text'][batch_id])
@@ -178,10 +156,8 @@
tp_writer["tp_time"][key + '#'] = str(ts_list)
tp_result_list.append(item)
return tp_result_list
-
+
return _forward
-
-
def inference_launch(mode, **kwargs):
@@ -190,6 +166,7 @@
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__":
--
Gitblit v1.9.1