diff --git a/src/functor/audiochunk.py b/src/functor/audiochunk.py index f7405ac..ad1fbae 100644 --- a/src/functor/audiochunk.py +++ b/src/functor/audiochunk.py @@ -5,16 +5,12 @@ """ import numpy as np -import logging +from src.utils.logger import get_module_logger from typing import List, Optional, Union from src.models import AudioBinary_Config # 配置日志 -logging.basicConfig( - level=logging.INFO, - format='%(asctime)s - %(name)s - %(levelname)s - %(message)s' -) -logger = logging.getLogger('AudioChunk') +logger = get_module_logger(__name__, level="INFO") class AudioChunk: """音频数据块管理类，用于存储和处理16KHz音频数据""" diff --git a/src/logic_trager.py b/src/logic_trager.py index 68c8cdd..18a3210 100644 --- a/src/logic_trager.py +++ b/src/logic_trager.py @@ -4,15 +4,10 @@ 逻辑触发器类 - 用于处理音频数据并触发相应的处理逻辑 """ -import logging +from src.utils.logger import get_module_logger from typing import Any, Dict, Type, Callable - # 配置日志 -logging.basicConfig( - level=logging.INFO, - format='%(asctime)s - %(name)s - %(levelname)s - %(message)s' -) -logger = logging.getLogger('LogicTrager') +logger = get_module_logger(__name__, level="INFO") class AutoAfterMeta(type): """ @@ -143,7 +138,7 @@ class LogicTrager(metaclass=AutoAfterMeta): """ 音频处理 """ - print("LogicTrager push_audio_chunk [{}ms:{}ms] (len={})".format(chunk.start_time, chunk.end_time, len(chunk.chunk))) + logger.info("LogicTrager push_audio_chunk [{}ms:{}ms] (len={})".format(chunk.start_time, chunk.end_time, len(chunk.chunk))) self._audio_chunk.append(chunk) def __after__push_audio_chunk(self) -> None: @@ -162,6 +157,7 @@ class LogicTrager(metaclass=AutoAfterMeta): """ 压入结果队列后处理 """ + logger.info("FINISH Result=") pass def __call__(self): diff --git a/src/utils/logger.py b/src/utils/logger.py new file mode 100644 index 0000000..b8f5f12 --- /dev/null +++ b/src/utils/logger.py @@ -0,0 +1,91 @@ +import logging +import sys +from pathlib import Path +from typing import Optional + +def setup_logger( + name: str = None, + level: str = "INFO", + log_file: Optional[str] = None, + log_format: str = "%(asctime)s - %(name)s - %(levelname)s - %(message)s", + date_format: str = "%Y-%m-%d %H:%M:%S", +) -> logging.Logger: + """ + 设置并返回一个配置好的logger实例 + + Args: + name: logger的名称，默认为None（使用root logger） + level: 日志级别，默认为"INFO" + log_file: 日志文件路径，默认为None（仅控制台输出） + log_format: 日志格式 + date_format: 日期格式 + + Returns: + logging.Logger: 配置好的logger实例 + """ + # 获取logger实例 + logger = logging.getLogger(name) + + # 设置日志级别 + level = getattr(logging, level.upper()) + logger.setLevel(level) + + print(f"添加处理器 {name} {log_file} {log_format} {date_format}") + # 创建格式器 + formatter = logging.Formatter(log_format, date_format) + + # 添加控制台处理器 + console_handler = logging.StreamHandler(sys.stdout) + console_handler.setFormatter(formatter) + logger.addHandler(console_handler) + + # 如果指定了日志文件，添加文件处理器 + if log_file: + # 确保日志目录存在 + log_path = Path(log_file) + log_path.parent.mkdir(parents=True, exist_ok=True) + + file_handler = logging.FileHandler(log_file, encoding='utf-8') + file_handler.setFormatter(formatter) + logger.addHandler(file_handler) + + # 注意：移除了 propagate = False，允许日志传递 + return logger + +def setup_root_logger( + level: str = "INFO", + log_file: Optional[str] = None +) -> None: + """ + 配置根日志器 + + Args: + level: 日志级别 + log_file: 日志文件路径 + """ + setup_logger(None, level, log_file) + +def get_module_logger( + module_name: str, + level: Optional[str] = None, # 改为可选参数 + log_file: Optional[str] = None # 一般不需要单独指定 +) -> logging.Logger: + """ + 获取模块级别的logger + + Args: + module_name: 模块名称，通常传入__name__ + level: 可选的日志级别，如果不指定则继承父级配置 + log_file: 可选的日志文件路径，一般不需要指定 + """ + logger = logging.getLogger(module_name) + + # 只有显式指定了level才设置 + if level: + logger.setLevel(getattr(logging, level.upper())) + + # 只有显式指定了log_file才添加文件处理器 + if log_file: + setup_logger(module_name, level or "INFO", log_file) + + return logger \ No newline at end of file diff --git a/test_main.py b/test_main.py index 9f0c069..596385f 100644 --- a/test_main.py +++ b/test_main.py @@ -1,4 +1,22 @@ -from tests.modelsuse import vad_model_use_online_logic +from src.utils.logger import get_module_logger, setup_root_logger +from tests.modelsuse import vad_model_use_online_logic, asr_model_use_offline +import json +setup_root_logger(level="INFO",log_file="logs/test_main.log") +logger = get_module_logger(__name__) + +logger.info("开始测试") vad_result = vad_model_use_online_logic("tests/vad_example.wav") -print(vad_result) \ No newline at end of file +logger.info("测试结束") +if vad_result is None: + logger.warning("VAD结果为空") +else: + logger.info(f"VAD结果: {vad_result}") + +asr_result = asr_model_use_offline("tests/vad_example.wav") +# asr_result str->dict +setup_root_logger(level="INFO",log_file="logs/test_main.log") +result = asr_result[0]['sentence_info'] +for item in result: + #[{'start': 70, 'end': 2340, 'sentence': '试 错 的 过 程 很 简 单', 'timestamp': [[380, 620], [640, 740], [740, 940], [940, 1020], [1020, 1260], [1500, 1740], [1740, 1840], [1840, 2135]], 'spk': 0} + logger.info(f"spk[{item['spk']}] [{item['start']}ms:{item['end']}ms] {item['sentence'].replace(' ', '')}") \ No newline at end of file diff --git a/tests/modelsuse.py b/tests/modelsuse.py index 6aee9fa..0554e0c 100644 --- a/tests/modelsuse.py +++ b/tests/modelsuse.py @@ -58,8 +58,25 @@ def vad_model_use_online_logic(file_path: str) -> List[Dict[str, Any]]: # for item in items: # print(item) return None - - + +def asr_model_use_offline(file_path: str) -> List[Dict[str, Any]]: + from funasr import AutoModel + model = AutoModel(model="paraformer-zh", model_revision="v2.0.4", + vad_model="fsmn-vad", vad_model_revision="v2.0.4", + # punc_model="ct-punc-c", punc_model_revision="v2.0.4", + spk_model="cam++", spk_model_revision="v2.0.2", + spk_mode="vad_segment", + auto_update=False, + ) + + import soundfile + + from src.models import AudioBinary_Config + import soundfile + + speech, sample_rate = soundfile.read(file_path) + result = model.generate(speech) + return result if __name__ == "__main__": # vad_result = vad_model_use_online("tests/vad_example.wav")