Browse Source

Merge pull request #2154 from distiny-cool/ali_api

增加了使用阿里云进行语音识别的引擎
master
Saboteur7 GitHub 3 months ago
parent
commit
5b26066a4c
No known key found for this signature in database GPG Key ID: B5690EEEBB952194
4 changed files with 91 additions and 6 deletions
  1. +1
    -1
      config.py
  2. +64
    -0
      voice/ali/ali_api.py
  3. +24
    -4
      voice/ali/ali_voice.py
  4. +2
    -1
      voice/ali/config.json.template

+ 1
- 1
config.py View File

@@ -95,7 +95,7 @@ available_setting = {
"group_speech_recognition": False, # 是否开启群组语音识别
"voice_reply_voice": False, # 是否使用语音回复语音,需要设置对应语音合成引擎的api key
"always_reply_voice": False, # 是否一直使用语音回复
"voice_to_text": "openai", # 语音识别引擎,支持openai,baidu,google,azure
"voice_to_text": "openai", # 语音识别引擎,支持openai,baidu,google,ali,azure
"text_to_voice": "openai", # 语音合成引擎,支持openai,baidu,google,pytts(offline),ali,azure,elevenlabs,edge(online)
"text_to_voice_model": "tts-1",
"tts_voice_id": "alloy",


+ 64
- 0
voice/ali/ali_api.py View File

@@ -8,6 +8,7 @@ Description:

"""

import http.client
import json
import time
import requests
@@ -61,6 +62,69 @@ def text_to_speech_aliyun(url, text, appkey, token):

return output_file

def speech_to_text_aliyun(url, audioContent, appkey, token):
"""
使用阿里云的语音识别服务识别音频文件中的语音。

参数:
- url (str): 阿里云语音识别服务的端点URL。
- audioContent (byte): pcm音频数据。
- appkey (str): 您的阿里云appkey。
- token (str): 阿里云API的认证令牌。

返回值:
- str: 成功时输出识别到的文本,否则为None。
"""
format = 'pcm'
sample_rate = 16000
enablePunctuationPrediction = True
enableInverseTextNormalization = True
enableVoiceDetection = False

# 设置RESTful请求参数
request = url + '?appkey=' + appkey
request = request + '&format=' + format
request = request + '&sample_rate=' + str(sample_rate)

if enablePunctuationPrediction :
request = request + '&enable_punctuation_prediction=' + 'true'

if enableInverseTextNormalization :
request = request + '&enable_inverse_text_normalization=' + 'true'

if enableVoiceDetection :
request = request + '&enable_voice_detection=' + 'true'
host = 'nls-gateway-cn-shanghai.aliyuncs.com'

# 设置HTTPS请求头部
httpHeaders = {
'X-NLS-Token': token,
'Content-type': 'application/octet-stream',
'Content-Length': len(audioContent)
}

conn = http.client.HTTPSConnection(host)
conn.request(method='POST', url=request, body=audioContent, headers=httpHeaders)

response = conn.getresponse()
body = response.read()
try:
body = json.loads(body)
status = body['status']
if status == 20000000 :
result = body['result']
if result :
logger.info(f"阿里云语音识别到了:{result}")
conn.close()
return result
else :
logger.error(f"语音识别失败,状态码: {status}")
except ValueError:
logger.error(f"语音识别失败,收到非JSON格式的数据: {body}")
conn.close()
return None


class AliyunTokenGenerator:
"""


+ 24
- 4
voice/ali/ali_voice.py View File

@@ -15,9 +15,9 @@ import time

from bridge.reply import Reply, ReplyType
from common.log import logger
from voice.audio_convert import get_pcm_from_wav
from voice.voice import Voice
from voice.ali.ali_api import AliyunTokenGenerator
from voice.ali.ali_api import text_to_speech_aliyun
from voice.ali.ali_api import AliyunTokenGenerator, speech_to_text_aliyun, text_to_speech_aliyun
from config import conf


@@ -34,7 +34,8 @@ class AliVoice(Voice):
self.token = None
self.token_expire_time = 0
# 默认复用阿里云千问的 access_key 和 access_secret
self.api_url = config.get("api_url")
self.api_url_voice_to_text = config.get("api_url_voice_to_text")
self.api_url_text_to_voice = config.get("api_url_text_to_voice")
self.app_key = config.get("app_key")
self.access_key_id = conf().get("qwen_access_key_id") or config.get("access_key_id")
self.access_key_secret = conf().get("qwen_access_key_secret") or config.get("access_key_secret")
@@ -53,7 +54,7 @@ class AliVoice(Voice):
r'äöüÄÖÜáéíóúÁÉÍÓÚàèìòùÀÈÌÒÙâêîôûÂÊÎÔÛçÇñÑ,。!?,.]', '', text)
# 提取有效的token
token_id = self.get_valid_token()
fileName = text_to_speech_aliyun(self.api_url, text, self.app_key, token_id)
fileName = text_to_speech_aliyun(self.api_url_text_to_voice, text, self.app_key, token_id)
if fileName:
logger.info("[Ali] textToVoice text={} voice file name={}".format(text, fileName))
reply = Reply(ReplyType.VOICE, fileName)
@@ -61,6 +62,25 @@ class AliVoice(Voice):
reply = Reply(ReplyType.ERROR, "抱歉,语音合成失败")
return reply

def voiceToText(self, voice_file):
"""
将语音文件转换为文本。

:param voice_file: 要转换的语音文件。
:return: 返回一个Reply对象,其中包含转换得到的文本或错误信息。
"""
# 提取有效的token
token_id = self.get_valid_token()
logger.debug("[Ali] voice file name={}".format(voice_file))
pcm = get_pcm_from_wav(voice_file)
text = speech_to_text_aliyun(self.api_url_voice_to_text, pcm, self.app_key, token_id)
if text:
logger.info("[Ali] VoicetoText = {}".format(text))
reply = Reply(ReplyType.TEXT, text)
else:
reply = Reply(ReplyType.ERROR, "抱歉,语音识别失败")
return reply

def get_valid_token(self):
"""
获取有效的阿里云token。


+ 2
- 1
voice/ali/config.json.template View File

@@ -1,5 +1,6 @@
{
"api_url": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
"api_url_text_to_voice": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
"api_url_voice_to_text": "https://nls-gateway.cn-shanghai.aliyuncs.com/stream/v1/asr",
"app_key": "",
"access_key_id": "",
"access_key_secret": ""

Loading…
Cancel
Save