Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 15:13:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

update:抽离公共方法save_audio_to_file到父类

Browse Source
This commit is contained in:
hrz
2025-05-29 10:38:01 +08:00
parent 625d079168
commit d86a2cf9de
8 changed files with 19 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/asr/aliyun.py
-17
View File
@@ -3,8 +3,6 @@ import json
import asyncio
from typing import Optional, Tuple, List
import opuslib_next
import wave
import io
import os
import uuid
import hmac
@@ -165,21 +163,6 @@ class ASRProvider(ASRProviderBase):
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"""
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1) # 单声道
wf.setsampwidth(2) # 16-bit
wf.setframerate(self.sample_rate)
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
async def _send_request(self, pcm_data: bytes) -> Optional[str]:
"""发送请求到阿里云ASR服务"""
try:
main/xiaozhi-server/core/providers/asr/baidu.py
-14
View File
@@ -36,20 +36,6 @@ class ASRProvider(ASRProviderBase):
# 确保输出目录存在
os.makedirs(self.output_dir, exist_ok=True)
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2) # 2 bytes = 16-bit
wf.setframerate(16000)
wf.writeframes(b"".join(pcm_data))
return file_path
async def speech_to_text(
self, opus_data: List[bytes], session_id: str
) -> Tuple[Optional[str], Optional[str]]:
main/xiaozhi-server/core/providers/asr/base.py
+16 -4
View File
@@ -1,7 +1,10 @@
from abc import ABC, abstractmethod
from typing import Optional, Tuple, List
import os
import uuid
import wave
import opuslib_next
from abc import ABC, abstractmethod
from config.logger import setup_logging
from typing import Optional, Tuple, List
TAG = __name__
logger = setup_logging()
@@ -11,10 +14,19 @@ class ASRProviderBase(ABC):
def __init__(self):
self.audio_format = "opus"
@abstractmethod
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
pass
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2) # 2 bytes = 16-bit
wf.setframerate(16000)
wf.writeframes(b"".join(pcm_data))
return file_path
@abstractmethod
async def speech_to_text(
main/xiaozhi-server/core/providers/asr/doubao.py
+3 -21
View File
@@ -1,17 +1,13 @@
import time
import io
import wave
import os
from typing import Optional, Tuple, List
import uuid
import websockets
import json
import gzip
import opuslib_next
import websockets
from config.logger import setup_logging
from typing import Optional, Tuple, List
from core.providers.asr.base import ASRProviderBase
from config.logger import setup_logging
TAG = __name__
logger = setup_logging()
@@ -102,20 +98,6 @@ class ASRProvider(ASRProviderBase):
# 确保输出目录存在
os.makedirs(self.output_dir, exist_ok=True)
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2) # 2 bytes = 16-bit
wf.setframerate(16000)
wf.writeframes(b"".join(pcm_data))
return file_path
@staticmethod
def _generate_header(
message_type=CLIENT_FULL_REQUEST, message_type_specific_flags=NO_SEQUENCE
main/xiaozhi-server/core/providers/asr/fun_local.py
-14
View File
@@ -53,20 +53,6 @@ class ASRProvider(ASRProviderBase):
# device="cuda:0", # 启用GPU加速
)
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2) # 2 bytes = 16-bit
wf.setframerate(16000)
wf.writeframes(b"".join(pcm_data))
return file_path
async def speech_to_text(
self, opus_data: List[bytes], session_id: str
) -> Tuple[Optional[str], Optional[str]]:
main/xiaozhi-server/core/providers/asr/fun_server.py
-14
View File
@@ -43,20 +43,6 @@ class ASRProvider(ASRProviderBase):
self.ssl_context.check_hostname = False
self.ssl_context.verify_mode = ssl.CERT_NONE
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2) # 2 bytes = 16-bit
wf.setframerate(16000)
wf.writeframes(b"".join(pcm_data))
return file_path
async def _receive_responses(self, ws) -> None:
"""
Asynchronous generator to receive messages from the WebSocket.
main/xiaozhi-server/core/providers/asr/sherpa_onnx_local.py
-14
View File
@@ -84,20 +84,6 @@ class ASRProvider(ASRProviderBase):
use_itn=True,
)
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2) # 2 bytes = 16-bit
wf.setframerate(16000)
wf.writeframes(b"".join(pcm_data))
return file_path
def read_wave(self, wave_filename: str) -> Tuple[np.ndarray, int]:
"""
Args:
main/xiaozhi-server/core/providers/asr/tencent.py
-16
View File
@@ -8,8 +8,6 @@ import os
import uuid
from typing import Optional, Tuple, List
import wave
import opuslib_next
import requests
from core.providers.asr.base import ASRProviderBase
from config.logger import setup_logging
@@ -33,20 +31,6 @@ class ASRProvider(ASRProviderBase):
# 确保输出目录存在
os.makedirs(self.output_dir, exist_ok=True)
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
module_name = __name__.split(".")[-1]
file_name = f"asr_{module_name}_{session_id}_{uuid.uuid4()}.wav"
file_path = os.path.join(self.output_dir, file_name)
with wave.open(file_path, "wb") as wf:
wf.setnchannels(1)
wf.setsampwidth(2) # 2 bytes = 16-bit
wf.setframerate(16000)
wf.writeframes(b"".join(pcm_data))
return file_path
async def speech_to_text(
self, opus_data: List[bytes], session_id: str
) -> Tuple[Optional[str], Optional[str]]: