Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 07:03:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

add:asr赋值audio_format

Browse Source
This commit is contained in:
hrz
2025-05-08 11:11:28 +08:00
parent ba86b34a8c
commit c2e000f937
5 changed files with 72 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/handle/helloHandle.py
+2 -1
View File
@@ -28,7 +28,8 @@ async def handleHelloMessage(conn, msg_json):
format = audio_params.get("format")
logger.bind(tag=TAG).info(f"客户端音频格式: {format}")
conn.audio_format = format
conn.welcome_msg['audio_params'] = audio_params
conn.asr.set_audio_format(format)
conn.welcome_msg["audio_params"] = audio_params
await conn.websocket.send(json.dumps(conn.welcome_msg))
main/xiaozhi-server/core/providers/asr/aliyun.py
+59 -47
View File
@@ -20,62 +20,75 @@ from core.providers.asr.base import ASRProviderBase
TAG = __name__
logger = setup_logging()
class AccessToken:
@staticmethod
def _encode_text(text):
encoded_text = parse.quote_plus(text)
return encoded_text.replace('+', '%20').replace('*', '%2A').replace('%7E', '~')
return encoded_text.replace("+", "%20").replace("*", "%2A").replace("%7E", "~")
@staticmethod
def _encode_dict(dic):
keys = dic.keys()
dic_sorted = [(key, dic[key]) for key in sorted(keys)]
encoded_text = parse.urlencode(dic_sorted)
return encoded_text.replace('+', '%20').replace('*', '%2A').replace('%7E', '~')
return encoded_text.replace("+", "%20").replace("*", "%2A").replace("%7E", "~")
@staticmethod
def create_token(access_key_id, access_key_secret):
parameters = {'AccessKeyId': access_key_id,
'Action': 'CreateToken',
'Format': 'JSON',
'RegionId': 'cn-shanghai',
'SignatureMethod': 'HMAC-SHA1',
'SignatureNonce': str(uuid.uuid1()),
'SignatureVersion': '1.0',
'Timestamp': time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
'Version': '2019-02-28'}
parameters = {
"AccessKeyId": access_key_id,
"Action": "CreateToken",
"Format": "JSON",
"RegionId": "cn-shanghai",
"SignatureMethod": "HMAC-SHA1",
"SignatureNonce": str(uuid.uuid1()),
"SignatureVersion": "1.0",
"Timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
"Version": "2019-02-28",
}
# 构造规范化的请求字符串
query_string = AccessToken._encode_dict(parameters)
# print('规范化的请求字符串: %s' % query_string)
# 构造待签名字符串
string_to_sign = 'GET' + '&' + AccessToken._encode_text('/') + '&' + AccessToken._encode_text(query_string)
string_to_sign = (
"GET"
+ "&"
+ AccessToken._encode_text("/")
+ "&"
+ AccessToken._encode_text(query_string)
)
# print('待签名的字符串: %s' % string_to_sign)
# 计算签名
secreted_string = hmac.new(bytes(access_key_secret + '&', encoding='utf-8'),
bytes(string_to_sign, encoding='utf-8'),
hashlib.sha1).digest()
secreted_string = hmac.new(
bytes(access_key_secret + "&", encoding="utf-8"),
bytes(string_to_sign, encoding="utf-8"),
hashlib.sha1,
).digest()
signature = base64.b64encode(secreted_string)
# print('签名: %s' % signature)
# 进行URL编码
signature = AccessToken._encode_text(signature)
# print('URL编码后的签名: %s' % signature)
# 调用服务
full_url = 'http://nls-meta.cn-shanghai.aliyuncs.com/?Signature=%s&%s' % (signature, query_string)
full_url = "http://nls-meta.cn-shanghai.aliyuncs.com/?Signature=%s&%s" % (
signature,
query_string,
)
# print('url: %s' % full_url)
# 提交HTTP GET请求
response = requests.get(full_url)
if response.ok:
root_obj = response.json()
key = 'Token'
key = "Token"
if key in root_obj:
token = root_obj[key]['Id']
expire_time = root_obj[key]['ExpireTime']
token = root_obj[key]["Id"]
expire_time = root_obj[key]["ExpireTime"]
return token, expire_time
# print(response.text)
return None, None
class ASRProvider(ASRProviderBase):
def __init__(self, config: dict, delete_audio_file: bool):
"""阿里云ASR初始化"""
@@ -102,28 +115,23 @@ class ASRProvider(ASRProviderBase):
# 确保输出目录存在
os.makedirs(self.output_dir, exist_ok=True)
def _refresh_token(self):
"""刷新Token并记录过期时间"""
if self.access_key_id and self.access_key_secret:
self.token, expire_time_str = AccessToken.create_token(
self.access_key_id,
self.access_key_secret
self.access_key_id, self.access_key_secret
)
if not expire_time_str:
raise ValueError("无法获取有效的Token过期时间")
try:
#统一转换为字符串处理
# 统一转换为字符串处理
expire_str = str(expire_time_str).strip()
if expire_str.isdigit():
expire_time = datetime.fromtimestamp(int(expire_str))
else:
expire_time = datetime.strptime(
expire_str,
"%Y-%m-%dT%H:%M:%SZ"
)
expire_time = datetime.strptime(expire_str, "%Y-%m-%dT%H:%M:%SZ")
self.expire_time = expire_time.timestamp() - 60
except Exception as e:
raise ValueError(f"无效的过期时间格式: {expire_str}") from e
@@ -145,9 +153,12 @@ class ASRProvider(ASRProviderBase):
# f"过期时间 {datetime.fromtimestamp(self.expire_time)} | "
# f"剩余 {remaining:.2f}秒")
return time.time() > self.expire_time
def generate_filename(self, extension=".wav"):
return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
def generate_filename(self, extension=".wav"):
return os.path.join(
self.output_file,
f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
)
def _construct_request_url(self) -> str:
"""构造请求URL，包含参数"""
@@ -158,7 +169,6 @@ class ASRProvider(ASRProviderBase):
request += "&enable_inverse_text_normalization=true"
request += "&enable_voice_detection=false"
return request
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
@@ -170,7 +180,7 @@ class ASRProvider(ASRProviderBase):
wf.setnchannels(1) # 单声道
wf.setsampwidth(2) # 16-bit
wf.setframerate(self.sample_rate)
wf.writeframes(b''.join(pcm_data))
wf.writeframes(b"".join(pcm_data))
logger.bind(tag=TAG).debug(f"音频文件已保存至: {file_path}")
return file_path
@@ -180,9 +190,9 @@ class ASRProvider(ASRProviderBase):
try:
# 设置HTTP头
headers = {
'X-NLS-Token': self.token,
'Content-type': 'application/octet-stream',
'Content-Length': str(len(pcm_data))
"X-NLS-Token": self.token,
"Content-type": "application/octet-stream",
"Content-Length": str(len(pcm_data)),
}
# 创建连接并发送请求
@@ -190,12 +200,12 @@ class ASRProvider(ASRProviderBase):
request_url = self._construct_request_url()
loop = asyncio.get_event_loop()
await loop.run_in_executor(None, lambda: conn.request(
method='POST',
url=request_url,
body=pcm_data,
headers=headers
))
await loop.run_in_executor(
None,
lambda: conn.request(
method="POST", url=request_url, body=pcm_data, headers=headers
),
)
# 获取响应
response = await loop.run_in_executor(None, conn.getresponse)
@@ -205,10 +215,10 @@ class ASRProvider(ASRProviderBase):
# 解析响应
try:
body_json = json.loads(body)
status = body_json.get('status')
status = body_json.get("status")
if status == 20000000:
result = body_json.get('result', '')
result = body_json.get("result", "")
logger.bind(tag=TAG).debug(f"ASR结果: {result}")
return result
else:
@@ -223,7 +233,9 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).error(f"ASR请求失败: {e}", exc_info=True)
return None
async def speech_to_text(self, opus_data: List[bytes], session_id: str) -> Tuple[Optional[str], Optional[str]]:
async def speech_to_text(
self, opus_data: List[bytes], session_id: str
) -> Tuple[Optional[str], Optional[str]]:
"""将语音数据转换为文本"""
if self._is_token_expired():
logger.warning("Token已过期，正在自动刷新...")
@@ -235,8 +247,8 @@ class ASRProvider(ASRProviderBase):
if self.audio_format == "pcm":
pcm_data = opus_data
else:
pcm_data = self.decode_opus(opus_data, session_id)
combined_pcm_data = b''.join(pcm_data)
pcm_data = self.decode_opus(opus_data)
combined_pcm_data = b"".join(pcm_data)
# 判断是否保存为WAV文件
if self.delete_audio_file:
@@ -254,4 +266,4 @@ class ASRProvider(ASRProviderBase):
except Exception as e:
logger.bind(tag=TAG).error(f"语音识别失败: {e}", exc_info=True)
return "", file_path
return "", file_path
main/xiaozhi-server/core/providers/asr/doubao.py
+1 -1
View File
@@ -253,7 +253,7 @@ class ASRProvider(ASRProviderBase):
if self.audio_format == "pcm":
pcm_data = opus_data
else:
pcm_data = self.decode_opus(opus_data, session_id)
pcm_data = self.decode_opus(opus_data)
combined_pcm_data = b"".join(pcm_data)
# 判断是否保存为WAV文件
main/xiaozhi-server/core/providers/asr/fun_local.py
+9 -5
View File
@@ -44,7 +44,7 @@ class ASRProvider(ASRProviderBase):
model=self.model_dir,
vad_kwargs={"max_single_segment_time": 30000},
disable_update=True,
hub="hf"
hub="hf",
# device="cuda:0", # 启用GPU加速
)
@@ -62,7 +62,9 @@ class ASRProvider(ASRProviderBase):
return file_path
async def speech_to_text(self, opus_data: List[bytes], session_id: str) -> Tuple[Optional[str], Optional[str]]:
async def speech_to_text(
self, opus_data: List[bytes], session_id: str
) -> Tuple[Optional[str], Optional[str]]:
"""语音转文本主处理逻辑"""
file_path = None
try:
@@ -70,8 +72,8 @@ class ASRProvider(ASRProviderBase):
if self.audio_format == "pcm":
pcm_data = opus_data
else:
pcm_data = self.decode_opus(opus_data, session_id)
pcm_data = self.decode_opus(opus_data)
combined_pcm_data = b"".join(pcm_data)
# 判断是否保存为WAV文件
@@ -90,7 +92,9 @@ class ASRProvider(ASRProviderBase):
batch_size_s=60,
)
text = rich_transcription_postprocess(result[0]["text"])
logger.bind(tag=TAG).debug(f"语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text}")
logger.bind(tag=TAG).debug(
f"语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text}"
)
return text, file_path
main/xiaozhi-server/core/providers/asr/sherpa_onnx_local.py
+1 -1
View File
@@ -132,7 +132,7 @@ class ASRProvider(ASRProviderBase):
if self.audio_format == "pcm":
pcm_data = opus_data
else:
pcm_data = self.decode_opus(opus_data, session_id)
pcm_data = self.decode_opus(opus_data)
file_path = self.save_audio_to_file(pcm_data, session_id)
logger.bind(tag=TAG).debug(
f"音频文件保存耗时: {time.time() - start_time:.3f}s | 路径: {file_path}"