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

update:合并main分支

Browse Source
This commit is contained in:
hrz
2025-05-08 11:31:12 +08:00
parent 7f34447ace
commit 64f10b28e7
5 changed files with 19 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/handle/helloHandle.py
+1 -2
View File
@@ -1,5 +1,4 @@
import json
from config.logger import setup_logging
from core.handle.sendAudioHandle import send_stt_message
from core.utils.util import remove_punctuation_and_length
import shutil
@@ -25,7 +24,7 @@ async def handleHelloMessage(conn, msg_json):
audio_params = msg_json.get("audio_params")
if audio_params:
format = audio_params.get("format")
logger.bind(tag=TAG).info(f"客户端音频格式: {format}")
conn.logger.bind(tag=TAG).info(f"客户端音频格式: {format}")
conn.audio_format = format
conn.asr.set_audio_format(format)
conn.welcome_msg["audio_params"] = audio_params
main/xiaozhi-server/core/handle/receiveAudioHandle.py
+5 -5
View File
@@ -5,7 +5,7 @@ from core.handle.sendAudioHandle import send_stt_message
from core.handle.intentHandler import handle_user_intent
from core.utils.output_counter import check_device_output_limit
from core.handle.ttsReportHandle import enqueue_tts_report
from core.providers.tts.base import audio_to_opus_data
from core.utils.util import audio_to_data
TAG = __name__
@@ -111,7 +111,7 @@ async def max_out_size(conn):
conn.tts_last_text_index = 0
conn.llm_finish_task = True
file_path = "config/assets/max_output_size.wav"
opus_packets, _ = audio_to_opus_data(file_path)
opus_packets, _ = audio_to_data(file_path)
conn.audio_play_queue.put((opus_packets, text, 0))
conn.close_after_chat = True
@@ -133,7 +133,7 @@ async def check_bind_device(conn):
# 播放提示音
music_path = "config/assets/bind_code.wav"
opus_packets, _ = audio_to_opus_data(music_path)
opus_packets, _ = audio_to_data(music_path)
conn.audio_play_queue.put((opus_packets, text, 0))
# 逐个播放数字
@@ -141,7 +141,7 @@ async def check_bind_device(conn):
try:
digit = conn.bind_code[i]
num_path = f"config/assets/bind_code/{digit}.wav"
num_packets, _ = audio_to_opus_data(num_path)
num_packets, _ = audio_to_data(num_path)
conn.audio_play_queue.put((num_packets, None, i + 1))
except Exception as e:
conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
@@ -153,5 +153,5 @@ async def check_bind_device(conn):
conn.tts_last_text_index = 0
conn.llm_finish_task = True
music_path = "config/assets/bind_not_found.wav"
opus_packets, _ = audio_to_opus_data(music_path)
opus_packets, _ = audio_to_data(music_path)
conn.audio_play_queue.put((opus_packets, text, 0))
main/xiaozhi-server/core/handle/sendAudioHandle.py
+1 -1
View File
@@ -115,7 +115,7 @@ async def send_tts_message(conn, state, text=None):
stop_tts_notify_voice = conn.config.get(
"stop_tts_notify_voice", "config/assets/tts_notify.mp3"
)
audios, duration = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
audios, _ = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
await sendAudio(conn, audios)
# 清除服务端讲话状态
conn.clearSpeakStatus()
main/xiaozhi-server/core/providers/tts/base.py
+1 -50
View File
@@ -56,56 +56,7 @@ class TTSProviderBase(ABC):
def audio_to_pcm_data(self, audio_file_path):
"""音频文件转换为PCM编码"""
return audio_to_data(audio_file_path, is_opus=False)
def audio_to_opus_data(self, audio_file_path):
"""音频文件转换为Opus编码"""
return audio_to_data(audio_file_path, is_opus=True)
def audio_to_data(self, audio_file_path, is_opus=True):
# 获取文件后缀名
file_type = os.path.splitext(audio_file_path)[1]
if file_type:
file_type = file_type.lstrip(".")
# 读取音频文件，-nostdin 参数：不要从标准输入读取数据，否则FFmpeg会阻塞
audio = AudioSegment.from_file(
audio_file_path, format=file_type, parameters=["-nostdin"]
)
# 转换为单声道/16kHz采样率/16位小端编码（确保与编码器匹配）
audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2)
# 音频时长(秒)
duration = len(audio) / 1000.0
# 获取原始PCM数据（16位小端）
raw_data = audio.raw_data
# 初始化Opus编码器
encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO)
# 编码参数
frame_duration = 60 # 60ms per frame
frame_size = int(16000 * frame_duration / 1000) # 960 samples/frame
datas = []
# 按帧处理所有音频数据（包括最后一帧可能补零）
for i in range(0, len(raw_data), frame_size * 2): # 16bit=2bytes/sample
# 获取当前帧的二进制数据
chunk = raw_data[i : i + frame_size * 2]
# 如果最后一帧不足，补零
if len(chunk) < frame_size * 2:
chunk += b"\x00" * (frame_size * 2 - len(chunk))
if is_opus:
# 转换为numpy数组处理
np_frame = np.frombuffer(chunk, dtype=np.int16)
# 编码Opus数据
frame_data = encoder.encode(np_frame.tobytes(), frame_size)
else:
frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk)
datas.append(frame_data)
return datas, duration
main/xiaozhi-server/core/utils/util.py
+11 -9
View File
@@ -862,8 +862,7 @@ def analyze_emotion(text):
return top_emotions[0] # 如果都不在优先级列表里，返回第一个
def audio_to_opus_data(audio_file_path):
"""音频文件转换为Opus编码"""
def audio_to_data(audio_file_path, is_opus=True):
# 获取文件后缀名
file_type = os.path.splitext(audio_file_path)[1]
if file_type:
@@ -889,7 +888,7 @@ def audio_to_opus_data(audio_file_path):
frame_duration = 60 # 60ms per frame
frame_size = int(16000 * frame_duration / 1000) # 960 samples/frame
opus_datas = []
datas = []
# 按帧处理所有音频数据（包括最后一帧可能补零）
for i in range(0, len(raw_data), frame_size * 2): # 16bit=2bytes/sample
# 获取当前帧的二进制数据
@@ -899,14 +898,17 @@ def audio_to_opus_data(audio_file_path):
if len(chunk) < frame_size * 2:
chunk += b"\x00" * (frame_size * 2 - len(chunk))
# 转换为numpy数组处理
np_frame = np.frombuffer(chunk, dtype=np.int16)
if is_opus:
# 转换为numpy数组处理
np_frame = np.frombuffer(chunk, dtype=np.int16)
# 编码Opus数据
frame_data = encoder.encode(np_frame.tobytes(), frame_size)
else:
frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk)
# 编码Opus数据
opus_data = encoder.encode(np_frame.tobytes(), frame_size)
opus_datas.append(opus_data)
datas.append(frame_data)
return opus_datas, duration
return datas, duration
def check_vad_update(before_config, new_config):