Merge branch 'master' of https://bdgit.educoder.net/pcffgoxks/daomangzhang

src/Guide_stick_system/run/run.py

@@ -0,0 +1,152 @@
+import sys
+import os
+import subprocess
+import time
+import logging
+import glob
+# 设置日志配置，将日志输出到log.txt文件中，并附加运行的时间
+logging.basicConfig(level=logging.INFO,
+                    format='%(asctime)s - %(levelname)s - %(message)s',
+                    filename='/home/pi/Desktop/al/run/log.txt',
+                    filemode='a')
+
+# 添加其他文件夹的路径到sys.path
+sys.path.append('/home/pi/Desktop/voice_assistant')
+sys.path.append('/home/pi/Desktop/Guide_stick_system')
+sys.path.append('/home/pi/Desktop/manage/itt')
+
+import New 
+import wenzi
+import main
+# 设置文件路径
+text_file = "/home/pi/Desktop/manage/demo.txt"
+output_file = "/home/pi/Desktop/Guide_stick_system/run/output.mp3"
+vlc_path = 'vlc'
+remind_path = 'remind.wav'
+error_path = 'error.wav'
+directory = '/home/pi/Desktop/manage/*.txt'
+img_path = '/home/pi/Desktop/manage/img'
+marker = 0 
+consecutive_errors = 0 
+
+def get_latest_message(file_path, marker):
+    try:
+        with open(file_path, "r", encoding="utf-8") as f:
+            f.seek(marker)  # 移动到上次读取的位置
+            latest_message = f.read()
+            new_marker = f.tell()  # 获取新的位置标记
+        return latest_message, new_marker
+    except FileNotFoundError:
+        logging.error(f"文件未找到: {file_path}")
+        return "", 0
+    except PermissionError:
+        logging.error(f"没有权限读取文件: {file_path}")
+        return "", 0
+    except Exception as e:
+        logging.error(f"读取文件时发生错误: {e}")
+        return "", 0
+
+def log_demo_text():
+    if os.path.isfile(text_file):
+        with open(text_file, 'r') as file:
+            text = file.read()
+            logging.info(text)
+    else:
+        logging.error('txt文件不存在')
+        
+def is_file_empty(file_path):
+    return os.path.getsize(file_path) == 0
+
+def is_new_message(file_path, marker):
+    with open(file_path, "r", encoding="utf-8") as f:
+        f.seek(0) 
+        current_message = f.read()
+        current_marker = f.tell()  
+    return current_message != ""
+
+def clear_text_content(file_path):
+    with open(file_path, "w") as file:
+        file.truncate()
+
+def get_latest_txt_filename(directory_path):
+    # 获取目录下所有的 .txt 文件
+    file_list = glob.glob(os.path.join(directory_path, '*.txt'))
+
+    # 如果文件列表不为空
+    if file_list:
+        # 按修改时间排序，获取最新的文件
+        latest_file = max(file_list, key=os.path.getmtime)
+        return latest_file
+    else:
+        logging.error("没有找到 .txt 文件")
+        return None
+    
+def main():
+    wenzi.ensure_pytesseract_installed()  
+    wenzi.ensure_tesseract_executable_configured()
+
+    while True:
+        try:
+            # 初始化检测器
+            config = main.load_config()
+            detector = main.initialize_detector(config)
+            if detector is None:
+                return
+
+            # 检测图像中的对象
+            img_path = main.config['img_path']
+            detections = main.detect_objects(detector, img_path)
+            
+            # 可视化结果
+            main.visualize_results(img_path, detections)
+
+            #图像转文本
+            if not os.path.exists(img_path):  
+                logging.error(f"图片 {img_path} 不存在，等待下一张...")  
+                time.sleep(1)  
+                continue  
+            text = wenzi.image_to_text(img_path)  
+            if text:  
+                with open(text_file, 'w', encoding='utf-8') as file:  
+                    file.write(text)  
+                logging.info(f"图片的识别结果已保存到 {text_file}")  
+            else:  
+                logging.info(f"无法识别图片中的文字。")  
+            
+            #读取文本信息
+            content =  get_latest_txt_filename(directory)
+            if content:
+                logging.info(content)
+            latest_message, marker = get_latest_message(content, marker)
+            if is_file_empty(text_file):
+                time.sleep(2)
+                continue
+
+            #文本转语音
+            log_demo_text()
+            logging.info(f"转换文本到语音: {text_file}")
+            New.text_to_speech(latest_message, output_file)
+            logging.info(f"语音文件已生成: {output_file}")
+            clear_text_content(text_file)
+            logging.info(f"播放音频文件: {remind_path}")
+            subprocess.call([vlc_path, '--play-and-exit', remind_path])
+            time.sleep(1)
+            logging.info(f"播放音频文件: {output_file}")
+            subprocess.call([vlc_path, '--play-and-exit', output_file])
+            time.sleep(1)
+            marker = 0  
+            consecutive_errors = 0
+            pass
+            
+        except Exception as e:
+            logging.error(f"发生错误: {e}")
+            time.sleep(1)
+            consecutive_errors += 1
+            time.sleep(1)
+            if consecutive_errors >= 3:  
+                logging.info(f"播放音频文件: {error_path}")
+                subprocess.call([vlc_path, '--play-and-exit', error_path])
+                consecutive_errors = 0  
+
+if __name__ == "__main__":  
+    main()

src/Guide_stick_system/run/run.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+/usr/bin/python3 /home/pi/Desktop/al/run.py

src/Guide_stick_system/xfvoice/samples/remind/Makefile

@@ -1,32 +1,32 @@
-#common makefile header
-
-DIR_INC = ../../include
-DIR_BIN = ../../bin
-DIR_LIB = ../../libs
-
-TARGET	= output
-BIN_TARGET = $(DIR_BIN)/$(TARGET)
-
-CROSS_COMPILE = 
-CFLAGS = -g -Wall -I$(DIR_INC)
-
-ifdef LINUX64
-LDFLAGS := -L$(DIR_LIB)/x64
-else
-LDFLAGS := -L$(DIR_LIB)/x86 
-endif
-LDFLAGS += -lmsc -lrt -ldl -lpthread -lstdc++
-
-OBJECTS := $(patsubst %.c,%.o,$(wildcard *.c))
-
-$(BIN_TARGET) : $(OBJECTS)
-	$(CROSS_COMPILE)gcc $(CFLAGS) $^ -o $@ $(LDFLAGS)
-
-%.o : %.c
-	$(CROSS_COMPILE)gcc -c $(CFLAGS) $< -o $@
-clean:
-	@rm -f *.o $(BIN_TARGET)
-
-.PHONY:clean
-
-#common makefile foot
+#common makefile header
+
+DIR_INC = ../../include
+DIR_BIN = ../../bin
+DIR_LIB = ../../libs
+
+TARGET	= error
+BIN_TARGET = $(DIR_BIN)/$(TARGET)
+
+CROSS_COMPILE = 
+CFLAGS = -g -Wall -I$(DIR_INC)
+
+ifdef LINUX64
+LDFLAGS := -L$(DIR_LIB)/x64
+else
+LDFLAGS := -L$(DIR_LIB)/x86 
+endif
+LDFLAGS += -lmsc -lrt -ldl -lpthread -lstdc++
+
+OBJECTS := $(patsubst %.c,%.o,$(wildcard *.c))
+
+$(BIN_TARGET) : $(OBJECTS)
+	$(CROSS_COMPILE)gcc $(CFLAGS) $^ -o $@ $(LDFLAGS)
+
+%.o : %.c
+	$(CROSS_COMPILE)gcc -c $(CFLAGS) $< -o $@
+clean:
+	@rm -f *.o $(BIN_TARGET)
+
+.PHONY:clean
+
+#common makefile foot

src/Guide_stick_system/xfvoice/samples/remind/remind.c

@@ -1,186 +1,169 @@
-/*
-* 语音合成（Text To Speech，TTS）技术能够自动将任意文字实时转换为连续的
-* 自然语音，是一种能够在任何时间、任何地点，向任何人提供语音信息服务的
-* 高效便捷手段，非常符合信息时代海量数据、动态更新和个性化查询的需求。
-*/
-#include <string.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <unistd.h>
-#include <errno.h>
-#include "../../include/qtts.h"
-#include "../../include/msp_cmn.h"
-#include "../../include/msp_errors.h"
-typedef int SR_DWORD;
-typedef short int SR_WORD ;
-
-/* wav音频头部格式 */
-typedef struct _wave_pcm_hdr
-{
-	char            riff[4];                // = "RIFF"
-	int				size_8;                 // = FileSize - 8
-	char            wave[4];                // = "WAVE"
-	char            fmt[4];                 // = "fmt "
-	int				fmt_size;				// = 下一个结构体的大小 : 16
-
-	short int       format_tag;             // = PCM : 1
-	short int       channels;               // = 通道数 : 1
-	int				samples_per_sec;        // = 采样率 : 8000 | 6000 | 11025 | 16000
-	int				avg_bytes_per_sec;      // = 每秒字节数 : samples_per_sec * bits_per_sample / 8
-	short int       block_align;            // = 每采样点字节数 : wBitsPerSample / 8
-	short int       bits_per_sample;        // = 量化比特数: 8 | 16
-
-	char            data[4];                // = "data";
-	int				data_size;              // = 纯数据长度 : FileSize - 44 
-} wave_pcm_hdr;
-
-/* 默认wav音频头部数据 */
-wave_pcm_hdr default_wav_hdr = 
-{
-	{ 'R', 'I', 'F', 'F' },
-	0,
-	{'W', 'A', 'V', 'E'},
-	{'f', 'm', 't', ' '},
-	16,
-	1,
-	1,
-	16000,
-	32000,
-	2,
-	16,
-	{'d', 'a', 't', 'a'},
-	0  
-};
-/* 文本合成 */
-int text_to_speech(const char* src_text, const char* des_path, const char* params)
-{
-	int          ret          = -1;
-	FILE*        fp           = NULL;
-	const char*  sessionID    = NULL;
-	unsigned int audio_len    = 0;
-	wave_pcm_hdr wav_hdr      = default_wav_hdr;
-	int          synth_status = MSP_TTS_FLAG_STILL_HAVE_DATA;
-
-	if (NULL == src_text || NULL == des_path)
-	{
-		printf("params is error!\n");
-		return ret;
-	}
-	fp = fopen(des_path, "wb");
-	if (NULL == fp)
-	{
-		printf("open %s error.\n", des_path);
-		return ret;
-	}
-	/* 开始合成 */
-	sessionID = QTTSSessionBegin(params, &ret);
-	if (MSP_SUCCESS != ret)
-	{
-		printf("QTTSSessionBegin failed, error code: %d.\n", ret);
-		fclose(fp);
-		return ret;
-	}
-	ret = QTTSTextPut(sessionID, src_text, (unsigned int)strlen(src_text), NULL);
-	if (MSP_SUCCESS != ret)
-	{
-		printf("QTTSTextPut failed, error code: %d.\n",ret);
-		QTTSSessionEnd(sessionID, "TextPutError");
-		fclose(fp);
-		return ret;
-	}
-	printf("正在合成 ...\n");
-	fwrite(&wav_hdr, sizeof(wav_hdr) ,1, fp); //添加wav音频头，使用采样率为16000
-	while (1) 
-	{
-		/* 获取合成音频 */
-		const void* data = QTTSAudioGet(sessionID, &audio_len, &synth_status, &ret);
-		if (MSP_SUCCESS != ret)
-			break;
-		if (NULL != data)
-		{
-			fwrite(data, audio_len, 1, fp);
-		    wav_hdr.data_size += audio_len; //计算data_size大小
-		}
-		if (MSP_TTS_FLAG_DATA_END == synth_status)
-			break;
-	}
-	printf("\n");
-	if (MSP_SUCCESS != ret)
-	{
-		printf("QTTSAudioGet failed, error code: %d.\n",ret);
-		QTTSSessionEnd(sessionID, "AudioGetError");
-		fclose(fp);
-		return ret;
-	}
-	/* 修正wav文件头数据的大小 */
-	wav_hdr.size_8 += wav_hdr.data_size + (sizeof(wav_hdr) - 8);
-	
-	/* 将修正过的数据写回文件头部,音频文件为wav格式 */
-	fseek(fp, 4, 0);
-	fwrite(&wav_hdr.size_8,sizeof(wav_hdr.size_8), 1, fp); //写入size_8的值
-	fseek(fp, 40, 0); //将文件指针偏移到存储data_size值的位置
-	fwrite(&wav_hdr.data_size,sizeof(wav_hdr.data_size), 1, fp); //写入data_size的值
-	fclose(fp);
-	fp = NULL;
-	/* 合成完毕 */
-	ret = QTTSSessionEnd(sessionID, "Normal");
-	if (MSP_SUCCESS != ret)
-	{
-		printf("QTTSSessionEnd failed, error code: %d.\n",ret);
-	}
-
-	return ret;
-}
-
-int main(int argc, char* argv[])
-{
-	int         ret                  = MSP_SUCCESS;
-	const char* login_params         = "appid = ee5efae8, work_dir = .";//登录参数,appid与msc库绑定,请勿随意改动
-	/*
-	* rdn:           合成音频数字发音方式
-	* volume:        合成音频的音量
-	* pitch:         合成音频的音调
-	* speed:         合成音频对应的语速
-	* voice_name:    合成发音人
-	* sample_rate:   合成音频采样率
-	* text_encoding: 合成文本编码格式
-	*
-	*/
-	const char* session_begin_params = "engine_type = local,voice_name=xiaoyan, text_encoding = UTF8, tts_res_path = fo|res/tts/xiaoyan.jet;fo|res/tts/common.jet, sample_rate = 16000, speed = 50, volume = 50, pitch = 50, rdn = 2";
-	const char* filename             = "output.wav"; //合成的语音文件名称
-	const char* text                 = "欢迎使用轻便型导盲杖，此产品主要适用于盲人，为盲人出行进行安全的指导，解决盲人出现问题"; //合成文本
-	/* 用户登录 */
-	ret = MSPLogin(NULL, NULL, login_params); //第一个参数是用户名，第二个参数是密码，第三个参数是登录参数，用户名和密码可在http://www.xfyun.cn注册获取
-	if (MSP_SUCCESS != ret)
-	{
-		printf("MSPLogin failed, error code: %d.\n", ret);
-		goto exit ;//登录失败，退出登录
-	}
-
-	printf("\n###########################################################################\n");
-	printf("## 语音合成（Text To Speech，TTS）技术能够自动将任意文字实时转换为连续的 ##\n");
-	printf("## 自然语音，是一种能够在任何时间、任何地点，向任何人提供语音信息服务的  ##\n");
-	printf("## 高效便捷手段，非常符合信息时代海量数据、动态更新和个性化查询的需求。  ##\n");
-	printf("###########################################################################\n\n");
-
-	/* 文本合成 */
-	printf("开始合成 ...\n");
-	ret = text_to_speech(text, filename, session_begin_params);
-	if (MSP_SUCCESS != ret)
-	{
-		printf("text_to_speech failed, error code: %d.\n", ret);
-	}
-	printf("合成完毕\n");
-
-exit:
-	printf("###########################################################################\n\n");
-	printf("###########################################################################\n\n");
-	printf("###########################################################################\n\n");
-	printf("###########################################################################\n\n");
-	printf("按任意键退出 ...\n");
-	getchar();
-	MSPLogout(); //退出登录
-
-	return 0;
-}
-
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include "../../include/qtts.h"
+#include "../../include/msp_cmn.h"
+#include "../../include/msp_errors.h"
+typedef int SR_DWORD;
+typedef short int SR_WORD ;
+
+/* wav音频头部格式 */
+typedef struct _wave_pcm_hdr
+{
+	char            riff[4];                // = "RIFF"
+	int				size_8;                 // = FileSize - 8
+	char            wave[4];                // = "WAVE"
+	char            fmt[4];                 // = "fmt "
+	int				fmt_size;				// = 下一个结构体的大小 : 16
+
+	short int       format_tag;             // = PCM : 1
+	short int       channels;               // = 通道数 : 1
+	int				samples_per_sec;        // = 采样率 : 8000 | 6000 | 11025 | 16000
+	int				avg_bytes_per_sec;      // = 每秒字节数 : samples_per_sec * bits_per_sample / 8
+	short int       block_align;            // = 每采样点字节数 : wBitsPerSample / 8
+	short int       bits_per_sample;        // = 量化比特数: 8 | 16
+
+	char            data[4];                // = "data";
+	int				data_size;              // = 纯数据长度 : FileSize - 44 
+} wave_pcm_hdr;
+
+/* 默认wav音频头部数据 */
+wave_pcm_hdr default_wav_hdr = 
+{
+	{ 'R', 'I', 'F', 'F' },
+	0,
+	{'W', 'A', 'V', 'E'},
+	{'f', 'm', 't', ' '},
+	16,
+	1,
+	1,
+	16000,
+	32000,
+	2,
+	16,
+	{'d', 'a', 't', 'a'},
+	0  
+};
+/* 文本合成 */
+int text_to_speech(const char* src_text, const char* des_path, const char* params)
+{
+	int          ret          = -1;
+	FILE*        fp           = NULL;
+	const char*  sessionID    = NULL;
+	unsigned int audio_len    = 0;
+	wave_pcm_hdr wav_hdr      = default_wav_hdr;
+	int          synth_status = MSP_TTS_FLAG_STILL_HAVE_DATA;
+
+	if (NULL == src_text || NULL == des_path)
+	{
+		printf("params is error!\n");
+		return ret;
+	}
+	fp = fopen(des_path, "wb");
+	if (NULL == fp)
+	{
+		printf("open %s error.\n", des_path);
+		return ret;
+	}
+	/* 开始合成 */
+	sessionID = QTTSSessionBegin(params, &ret);
+	if (MSP_SUCCESS != ret)
+	{
+		printf("QTTSSessionBegin failed, error code: %d.\n", ret);
+		fclose(fp);
+		return ret;
+	}
+	ret = QTTSTextPut(sessionID, src_text, (unsigned int)strlen(src_text), NULL);
+	if (MSP_SUCCESS != ret)
+	{
+		printf("QTTSTextPut failed, error code: %d.\n",ret);
+		QTTSSessionEnd(sessionID, "TextPutError");
+		fclose(fp);
+		return ret;
+	}
+	printf("正在合成 ...\n");
+	fwrite(&wav_hdr, sizeof(wav_hdr) ,1, fp); //添加wav音频头，使用采样率为16000
+	while (1) 
+	{
+		/* 获取合成音频 */
+		const void* data = QTTSAudioGet(sessionID, &audio_len, &synth_status, &ret);
+		if (MSP_SUCCESS != ret)
+			break;
+		if (NULL != data)
+		{
+			fwrite(data, audio_len, 1, fp);
+		    wav_hdr.data_size += audio_len; //计算data_size大小
+		}
+		if (MSP_TTS_FLAG_DATA_END == synth_status)
+			break;
+	}
+	printf("\n");
+	if (MSP_SUCCESS != ret)
+	{
+		printf("QTTSAudioGet failed, error code: %d.\n",ret);
+		QTTSSessionEnd(sessionID, "AudioGetError");
+		fclose(fp);
+		return ret;
+	}
+	/* 修正wav文件头数据的大小 */
+	wav_hdr.size_8 += wav_hdr.data_size + (sizeof(wav_hdr) - 8);
+	
+	/* 将修正过的数据写回文件头部,音频文件为wav格式 */
+	fseek(fp, 4, 0);
+	fwrite(&wav_hdr.size_8,sizeof(wav_hdr.size_8), 1, fp); //写入size_8的值
+	fseek(fp, 40, 0); //将文件指针偏移到存储data_size值的位置
+	fwrite(&wav_hdr.data_size,sizeof(wav_hdr.data_size), 1, fp); //写入data_size的值
+	fclose(fp);
+	fp = NULL;
+	/* 合成完毕 */
+	ret = QTTSSessionEnd(sessionID, "Normal");
+	if (MSP_SUCCESS != ret)
+	{
+		printf("QTTSSessionEnd failed, error code: %d.\n",ret);
+	}
+
+	return ret;
+}
+
+int main(int argc, char* argv[])
+{
+	int         ret                  = MSP_SUCCESS;
+	const char* login_params         = "appid = ee5efae8, work_dir = .";//登录参数,appid与msc库绑定,请勿随意改动
+	/*
+	* rdn:           合成音频数字发音方式
+	* volume:        合成音频的音量
+	* pitch:         合成音频的音调
+	* speed:         合成音频对应的语速
+	* voice_name:    合成发音人
+	* sample_rate:   合成音频采样率
+	* text_encoding: 合成文本编码格式
+	*
+	*/
+	const char* session_begin_params = "engine_type = local,voice_name=xiaoyan, text_encoding = UTF8, tts_res_path = fo|res/tts/xiaoyan.jet;fo|res/tts/common.jet, sample_rate = 16000, speed = 50, volume = 50, pitch = 50, rdn = 2";
+	const char* filename = 			   "/home/pi/Desktop/al/error.wav"; //合成的语音文件名称
+	const char* text                 = " 程序发生错误。"; //合成文本
+	/* 用户登录 */
+	ret = MSPLogin(NULL, NULL, login_params); //第一个参数是用户名，第二个参数是密码，第三个参数是登录参数，用户名和密码可在http://www.xfyun.cn注册获取
+	if (MSP_SUCCESS != ret)
+	{
+		printf("MSPLogin failed, error code: %d.\n", ret);
+		goto exit ;//登录失败，退出登录
+	}
+
+	/* 文本合成 */
+	printf("开始合成 ...\n");
+	ret = text_to_speech(text, filename, session_begin_params);
+	if (MSP_SUCCESS != ret)
+	{
+		printf("text_to_speech failed, error code: %d.\n", ret);
+	}
+	printf("合成完毕\n");
+
+exit:
+	MSPLogout(); //退出登录
+
+	return 0;
+}
+