赞
踩
今天朋友在群里面问有没有录音转文字的免费软件?我就去网上搜了一下,发现网上大多数是超出一定时长就收费的,而我朋友的音频比较多,加起来有几个小时,于是我想着能不能调用接口,用python实现这个功能。
上图是某在线平台的音频转文字功能,可以看到超出时长收费也是比较贵的。
因为之前了解到讯飞主要做这方面,所以我选择了讯飞的开发平台。
进入官网讯飞开放平台
注册登录后点击语音转写
再点击控制台创建应用即可。
创建完后会得到APPID和密钥(这个代码要用)。
创建完应用后我们可以先领取5小时体验包。
找到开发文档,里面有代码示例。
我用的是python示例,并按照需求改了一下代码。
# -*- coding: utf-8 -*- # # author: yanmeng2 # # 非实时转写调用demo import base64 import hashlib import hmac import json import os import time import re import requests lfasr_host = 'http://raasr.xfyun.cn/api' # 请求的接口名 api_prepare = '/prepare' api_upload = '/upload' api_merge = '/merge' api_get_progress = '/getProgress' api_get_result = '/getResult' # 文件分片大小10M file_piece_sice = 10485760 # ——————————————————转写可配置参数———————————————— # 参数可在官网界面(https://doc.xfyun.cn/rest_api/%E8%AF%AD%E9%9F%B3%E8%BD%AC%E5%86%99.html)查看,根据需求可自行在gene_params方法里添加修改 # 转写类型 lfasr_type = 0 # 是否开启分词 has_participle = 'false' has_seperate = 'true' # 多候选词个数 max_alternatives = 0 # 子用户标识 suid = '' class SliceIdGenerator: """slice id生成器""" def __init__(self): self.__ch = 'aaaaaaaaa`' def getNextSliceId(self): ch = self.__ch j = len(ch) - 1 while j >= 0: cj = ch[j] if cj != 'z': ch = ch[:j] + chr(ord(cj) + 1) + ch[j + 1:] break else: ch = ch[:j] + 'a' + ch[j + 1:] j = j - 1 self.__ch = ch return self.__ch class RequestApi(object): def __init__(self, appid, secret_key, upload_file_path): self.appid = appid self.secret_key = secret_key self.upload_file_path = upload_file_path # 根据不同的apiname生成不同的参数,本示例中未使用全部参数您可在官网(https://doc.xfyun.cn/rest_api/%E8%AF%AD%E9%9F%B3%E8%BD%AC%E5%86%99.html)查看后选择适合业务场景的进行更换 def gene_params(self, apiname, taskid=None, slice_id=None): appid = self.appid secret_key = self.secret_key upload_file_path = self.upload_file_path ts = str(int(time.time())) m2 = hashlib.md5() m2.update((appid + ts).encode('utf-8')) md5 = m2.hexdigest() md5 = bytes(md5, encoding='utf-8') # 以secret_key为key, 上面的md5为msg, 使用hashlib.sha1加密结果为signa signa = hmac.new(secret_key.encode('utf-8'), md5, hashlib.sha1).digest() signa = base64.b64encode(signa) signa = str(signa, 'utf-8') file_len = os.path.getsize(upload_file_path) file_name = os.path.basename(upload_file_path) param_dict = {} if apiname == api_prepare: # slice_num是指分片数量,如果您使用的音频都是较短音频也可以不分片,直接将slice_num指定为1即可 slice_num = int(file_len / file_piece_sice) + (0 if (file_len % file_piece_sice == 0) else 1) param_dict['app_id'] = appid param_dict['signa'] = signa param_dict['ts'] = ts param_dict['file_len'] = str(file_len) param_dict['file_name'] = file_name param_dict['slice_num'] = str(slice_num) elif apiname == api_upload: param_dict['app_id'] = appid param_dict['signa'] = signa param_dict['ts'] = ts param_dict['task_id'] = taskid param_dict['slice_id'] = slice_id elif apiname == api_merge: param_dict['app_id'] = appid param_dict['signa'] = signa param_dict['ts'] = ts param_dict['task_id'] = taskid param_dict['file_name'] = file_name elif apiname == api_get_progress or apiname == api_get_result: param_dict['app_id'] = appid param_dict['signa'] = signa param_dict['ts'] = ts param_dict['task_id'] = taskid return param_dict # 请求和结果解析,结果中各个字段的含义可参考:https://doc.xfyun.cn/rest_api/%E8%AF%AD%E9%9F%B3%E8%BD%AC%E5%86%99.html def gene_request(self, apiname, data, files=None, headers=None): response = requests.post(lfasr_host + apiname, data=data, files=files, headers=headers) result = json.loads(response.text) if result["ok"] == 0: if apiname=='/getResult': results=re.findall(r"\"onebest\":\"(.+?)\",",result['data']) print(results) upload_file_path = self.upload_file_path with open(str(upload_file_path)+".txt", "a", encoding='utf-8') as f: for i in results: f.write(i) print("{} success:".format(apiname) + str(result)) return result else: print("{} error:".format(apiname) + str(result)) exit(0) return result # 预处理 def prepare_request(self): return self.gene_request(apiname=api_prepare, data=self.gene_params(api_prepare)) # 上传 def upload_request(self, taskid, upload_file_path): file_object = open(upload_file_path, 'rb') try: index = 1 sig = SliceIdGenerator() while True: content = file_object.read(file_piece_sice) if not content or len(content) == 0: break files = { "filename": self.gene_params(api_upload).get("slice_id"), "content": content } response = self.gene_request(api_upload, data=self.gene_params(api_upload, taskid=taskid, slice_id=sig.getNextSliceId()), files=files) if response.get('ok') != 0: # 上传分片失败 print('upload slice fail, response: ' + str(response)) return False print('upload slice ' + str(index) + ' success') index += 1 finally: 'file index:' + str(file_object.tell()) file_object.close() return True # 合并 def merge_request(self, taskid): return self.gene_request(api_merge, data=self.gene_params(api_merge, taskid=taskid)) # 获取进度 def get_progress_request(self, taskid): return self.gene_request(api_get_progress, data=self.gene_params(api_get_progress, taskid=taskid)) # 获取结果 def get_result_request(self, taskid): return self.gene_request(api_get_result, data=self.gene_params(api_get_result, taskid=taskid)) def all_api_request(self): # 1. 预处理 pre_result = self.prepare_request() taskid = pre_result["data"] # 2 . 分片上传 self.upload_request(taskid=taskid, upload_file_path=self.upload_file_path) # 3 . 文件合并 self.merge_request(taskid=taskid) # 4 . 获取任务进度 while True: # 每隔20秒获取一次任务进度 progress = self.get_progress_request(taskid) progress_dic = progress if progress_dic['err_no'] != 0 and progress_dic['err_no'] != 26605: print('task error: ' + progress_dic['failed']) return else: data = progress_dic['data'] task_status = json.loads(data) if task_status['status'] == 9: print('task ' + taskid + ' finished') break print('The task ' + taskid + ' is in processing, task status: ' + str(data)) # 每次获取进度间隔20S time.sleep(20) # 5 . 获取结果 self.get_result_request(taskid=taskid) # 注意:如果出现requests模块报错:"NoneType" object has no attribute 'read', 请尝试将requests模块更新到2.20.0或以上版本(本demo测试版本为2.20.0) # 输入讯飞开放平台的appid,secret_key和待转写的文件路径 if __name__ == '__main__': api = RequestApi(appid="", secret_key="", upload_file_path=r"") api.all_api_request()
使用上面的代码需要加三处地方。
代码倒数第二行的appid和密钥用你自己的,文件路径是音频的文件路径。
上面是我的文件目录(音频时长大概五十多分钟)。
上面即为生成的TXT文本。
体验包的时长也被扣了,不过5小时是够用的(新用户最多可以领50小时)。
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。