import pyaudio import wave import pymysql import time from datetime import datetime from pydub import AudioSegment import uuid import os os.environ.setdefault("DJANGO_SETTINGS_MODULE", "aiDogProject.settings") import django django.setup() from aiDogApp.models import * from .generalRequest import req_url # Importing your generalRequest.py method # Audio recording settings SAMPLE_RATE = 16000 BIT_RATE = 16 CHANNELS = 1 RECORD_SECONDS = 2 CHUNK = 1024 FORMAT = pyaudio.paInt16 # 连接mysql数据库 # def get_db_connection(): # return pymysql.connect( # host='127.0.0.1', # port=3306, # user='root', # password='', # database='aidog' # ) # 录制音频 并存储为WAV文件 def record_audio(file_path,mp3_path, duration=4): # Audio settings sample_rate = 16000 channels = 1 bit_rate = pyaudio.paInt16 chunk_size = 1024 audio = pyaudio.PyAudio() # Start recording stream = audio.open(format=bit_rate, channels=channels, rate=sample_rate, input=True, frames_per_buffer=chunk_size) print("Recording...") frames = [] for _ in range(0, int(sample_rate / chunk_size * duration)): data = stream.read(chunk_size) frames.append(data) print("Recording complete.") # Stop and close the stream stream.stop_stream() stream.close() audio.terminate() # Save audio to file with wave.open(file_path, 'wb') as wf: wf.setnchannels(channels) wf.setsampwidth(audio.get_sample_size(bit_rate)) wf.setframerate(sample_rate) wf.writeframes(b''.join(frames)) # Convert to MP3 audio_segment = AudioSegment.from_wav(file_path) audio_segment.export(mp3_path, format="mp3") # Remove the intermediate WAV file os.remove(file_path) # Function to insert audio information into MySQL database def insert_voice_data(uid, feature_id, wav_file_path,command_type,record_time): try: # conn = get_db_connection() # cursor = conn.cursor() # 读取 WAV 文件 为二进制数据 with open(wav_file_path, 'rb') as wav_file: wav_data = wav_file.read() # 插入到声纹信息表中 # 口令类型（0：叫名字 1：坐下，2：站起，3：摇尾巴，4：走过来，5 抬左手，6：抬右手） if command_type == 0: # 口令类型（0：叫名字 # insert_query = """ # INSERT INTO voice_feature_info (uid, voice_feature_id, voice_name_command,command_type) # VALUES (%s, %s, %s, %s) # """ # # cursor.execute(insert_query, (uid, feature_id, wav_data, command_type)) VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id, voice_name_command=wav_data, record_time=record_time) elif command_type == 1: # 口令类型（1：坐下 VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id, voice_sit_command=wav_data, record_time=record_time) elif command_type == 2: # 口令类型（2：站起 VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id, voice_stand_command=wav_data, record_time=record_time ) elif command_type == 3: # 口令类型（3：摇尾巴 VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id, voice_wagtail_command=wav_data, record_time=record_time) else: # 口令类型（4：走过来 VoiceFeatureInfo.objects.filter(uid=uid, command_type=command_type).update(voice_feature_id=feature_id, voice_come_command=wav_data, record_time=record_time) # conn.commit() print(f"Data inserted into database for UID: {uid}") return True # 抛出异常 except Exception as err: print(f"Error: {err}") return False # finally: # cursor.close() # conn.close() file_path = './media/讯飞开放平台.mp3'#读取数据库路径下音源 APPId = "527f831f" APISecret = "YWE5MjI0MzA4NmM3MTNmNTNiMWJkYzE4" APIKey = "be5c37f3db1569737934240a0e3ad02d" # Main method to record audio, save locally, insert to DB, and call req_url() def process_voice_recording(uid,voice_feature_id, command_type): # 定义本地缓存路径 cache_directory = "audio_cache" if not os.path.exists(cache_directory): os.makedirs(cache_directory) # 创建一个唯一的文件名 timestamp = int(time.time()) timestamp11 = datetime.now().strftime('%Y-%m-%d %H:%M:%S') file_path = os.path.join(cache_directory, f"voice_{uid}_{timestamp}.wav") mp3_path=os.path.join(cache_directory, f"voice_{uid}_{timestamp}.mp3") # 录制wav音频 并存储到cache record_audio(file_path,mp3_path) # 插入到数据库 声纹信息表 if insert_voice_data(uid, voice_feature_id, mp3_path,command_type,timestamp11): # 如果插入成功，调用generalRequest.py里的第三方声纹识别API res='xxx' res=req_url(api_name='createFeature', APPId=APPId, APIKey=APIKey, APISecret=APISecret, file_path=mp3_path, featureId=voice_feature_id,groupId=uid) # 传参数 缓存音频路径，声纹id print(f"音频文件缓存在 {mp3_path} 并且传参到 req_url().") yy = datetime.today() end_timestamp = datetime.strftime(yy, '%Y-%m-%d %H:%M:%S') # return res return (f"音频文件缓存在 {mp3_path} 并且传参到 req_url().返回内容为{res}.请求时间为:---{timestamp11}.返回时间为:---{end_timestamp}") else: print("Failed to insert voice data into database.") return ("Failed to insert voice data into database.") # 移除缓存中的wav文件 # os.remove(file_path) # Example Usage: # if __name__ == "__main__": # user_uid = 'JTYNZP9O' # 用户ID # feature_id = 'sfggcvvh1212' # 用户声纹 ID # command_type=1 # # process_voice_recording(user_uid, feature_id,command_type)