Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-30 03:23:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into py_Text

Browse Source 
# Conflicts:
#	main/xiaozhi-server/core/handle/helloHandle.py
#	main/xiaozhi-server/core/providers/tts/base.py
This commit is contained in:
hrz
2025-06-07 22:48:23 +08:00
parent 50e6e4817b 6023af2f21
commit 29d90df9ea
37 changed files with 1968 additions and 581 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/tts/base.py
+13 -1
View File
@@ -37,6 +37,7 @@ class TTSProviderBase(ABC):
self.tts_text_queue = queue.Queue()
self.tts_audio_queue = queue.Queue()
self.tts_audio_first_sentence = True
self.before_stop_play_files = []
self.tts_text_buff = []
self.punctuations = (
@@ -52,6 +53,7 @@ class TTSProviderBase(ABC):
)
self.first_sentence_punctuations = (
"，",
"～",
"~",
"、",
",",
@@ -84,7 +86,9 @@ class TTSProviderBase(ABC):
try:
audio_bytes = asyncio.run(self.text_to_speak(text, None))
if audio_bytes:
audio_datas, _ = audio_bytes_to_data(audio_bytes, file_type=self.audio_file_type, is_opus=True)
audio_datas, _ = audio_bytes_to_data(
audio_bytes, file_type=self.audio_file_type, is_opus=True
)
return audio_datas
else:
max_repeat_time -= 1
@@ -355,6 +359,14 @@ class TTSProviderBase(ABC):
os.remove(tts_file)
return audio_datas
def _process_before_stop_play_files(self):
for tts_file, text in self.before_stop_play_files:
if tts_file and os.path.exists(tts_file):
audio_datas = self._process_audio_file(tts_file)
self.tts_audio_queue.put((SentenceType.MIDDLE, audio_datas, text))
self.before_stop_play_files.clear()
self.tts_audio_queue.put((SentenceType.LAST, [], None))
def _process_remaining_text(self):
"""处理剩余的文本并生成语音
main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
+4 -13
View File
@@ -153,7 +153,6 @@ class TTSProvider(TTSProviderBase):
self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
self.enable_two_way = True
self.tts_text = ""
self.before_stop_play_files = []
self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
sample_rate=16000, channels=1, frame_size_ms=60
)
@@ -194,7 +193,7 @@ class TTSProvider(TTSProviderBase):
try:
logger.bind(tag=TAG).debug("等待TTS文本队列消息...")
message = self.tts_text_queue.get(timeout=1)
logger.bind(tag=TAG).info(
logger.bind(tag=TAG).debug(
f"收到TTS任务｜{message.sentence_type.name} ｜ {message.content_type.name} | 会话ID: {self.conn.sentence_id}"
)
if self.conn.client_abort:
@@ -220,7 +219,7 @@ class TTSProvider(TTSProviderBase):
elif ContentType.TEXT == message.content_type:
if message.content_detail:
try:
logger.bind(tag=TAG).info(
logger.bind(tag=TAG).debug(
f"开始发送TTS文本: {message.content_detail}"
)
future = asyncio.run_coroutine_threadsafe(
@@ -228,7 +227,7 @@ class TTSProvider(TTSProviderBase):
loop=self.conn.loop,
)
future.result()
logger.bind(tag=TAG).info("TTS文本发送成功")
logger.bind(tag=TAG).debug("TTS文本发送成功")
except Exception as e:
logger.bind(tag=TAG).error(f"发送TTS文本失败: {str(e)}")
continue
@@ -249,7 +248,6 @@ class TTSProvider(TTSProviderBase):
loop=self.conn.loop,
)
future.result()
logger.bind(tag=TAG).info("TTS会话结束成功")
except Exception as e:
logger.bind(tag=TAG).error(f"结束TTS会话失败: {str(e)}")
continue
@@ -432,14 +430,7 @@ class TTSProvider(TTSProviderBase):
is_first_sentence = False
elif res.optional.event == EVENT_SessionFinished:
logger.bind(tag=TAG).debug(f"会话结束～～")
for tts_file, text in self.before_stop_play_files:
if tts_file and os.path.exists(tts_file):
audio_datas = self._process_audio_file(tts_file)
self.tts_audio_queue.put(
(SentenceType.MIDDLE, audio_datas, text)
)
self.before_stop_play_files.clear()
self.tts_audio_queue.put((SentenceType.LAST, [], None))
self._process_before_stop_play_files()
break
except websockets.ConnectionClosed:
logger.bind(tag=TAG).warning("WebSocket连接已关闭")
main/xiaozhi-server/core/providers/tts/linkerai.py
+227
View File
@@ -0,0 +1,227 @@
import queue
import asyncio
import traceback
import aiohttp
from config.logger import setup_logging
from core.utils.tts import MarkdownCleaner
from core.providers.tts.base import TTSProviderBase
from core.utils import opus_encoder_utils, textUtils
from core.providers.tts.dto.dto import SentenceType, ContentType, InterfaceType
TAG = __name__
logger = setup_logging()
class TTSProvider(TTSProviderBase):
def __init__(self, config, delete_audio_file):
super().__init__(config, delete_audio_file)
self.interface_type = InterfaceType.SINGLE_STREAM
self.access_token = config.get("access_token")
self.voice = config.get("voice")
self.api_url = config.get("api_url")
self.audio_format = "pcm"
self.before_stop_play_files = []
self.segment_count = 0 # 添加片段计数器
# 创建Opus编码器
self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
sample_rate=16000, channels=1, frame_size_ms=60
)
# 添加文本缓冲区
self.text_buffer = ""
# PCM缓冲区
self.pcm_buffer = bytearray()
###################################################################################
# linkerai单流式TTS重写父类的方法--开始
###################################################################################
def tts_text_priority_thread(self):
"""流式文本处理线程"""
while not self.conn.stop_event.is_set():
try:
message = self.tts_text_queue.get(timeout=1)
if message.sentence_type == SentenceType.FIRST:
# 初始化参数
self.tts_stop_request = False
self.processed_chars = 0
self.tts_text_buff = []
self.segment_count = 0
self.tts_audio_first_sentence = True
self.before_stop_play_files.clear()
elif ContentType.TEXT == message.content_type:
self.tts_text_buff.append(message.content_detail)
segment_text = self._get_segment_text()
if segment_text:
self.to_tts(segment_text)
elif ContentType.FILE == message.content_type:
logger.bind(tag=TAG).info(
f"添加音频文件到待播放列表: {message.content_file}"
)
self.before_stop_play_files.append(
(message.content_file, message.content_detail)
)
if message.sentence_type == SentenceType.LAST:
# 处理剩余的文本
self._process_remaining_text(True)
except queue.Empty:
continue
except Exception as e:
logger.bind(tag=TAG).error(
f"处理TTS文本失败: {str(e)}, 类型: {type(e).__name__}, 堆栈: {traceback.format_exc()}"
)
def _process_remaining_text(self, is_last=False):
"""处理剩余的文本并生成语音
Returns:
bool: 是否成功处理了文本
"""
full_text = "".join(self.tts_text_buff)
remaining_text = full_text[self.processed_chars :]
if remaining_text:
segment_text = textUtils.get_string_no_punctuation_or_emoji(remaining_text)
if segment_text:
self.to_tts(segment_text, is_last)
self.processed_chars += len(full_text)
else:
self._process_before_stop_play_files()
def to_tts(self, text, is_last=False):
try:
max_repeat_time = 5
text = MarkdownCleaner.clean_markdown(text)
try:
asyncio.run(self.text_to_speak(text, is_last))
except Exception as e:
logger.bind(tag=TAG).warning(
f"语音生成失败{5 - max_repeat_time + 1}次: {text}，错误: {e}"
)
max_repeat_time -= 1
if max_repeat_time > 0:
logger.bind(tag=TAG).info(
f"语音生成成功: {text}，重试{5 - max_repeat_time}次"
)
else:
logger.bind(tag=TAG).error(
f"语音生成失败: {text}，请检查网络或服务是否正常"
)
except Exception as e:
logger.bind(tag=TAG).error(f"Failed to generate TTS file: {e}")
finally:
return None
###################################################################################
# linkerai单流式TTS重写父类的方法--结束
###################################################################################
async def text_to_speak(self, text, is_last):
"""流式处理TTS音频，每句只推送一次音频列表"""
await self._tts_request(text, is_last)
async def close(self):
"""资源清理"""
await super().close()
if hasattr(self, "opus_encoder"):
self.opus_encoder.close()
async def _tts_request(self, text: str, is_last: bool) -> None:
params = {
"tts_text": text,
"spk_id": self.voice,
"frame_durition": 60,
"stream": "true",
"target_sr": 16000,
"audio_format": "pcm",
"instruct_text": "请生成一段自然流畅的语音",
}
headers = {
"Authorization": f"Bearer {self.access_token}",
"Content-Type": "application/json",
}
# 一帧 PCM 所需字节数：60 ms × 16 kHz × 1 ch × 2 B = 1 920
frame_bytes = int(
self.opus_encoder.sample_rate
* self.opus_encoder.channels # 1
* self.opus_encoder.frame_size_ms
/ 1000
* 2
) # 16-bit = 2 bytes
try:
async with aiohttp.ClientSession() as session:
async with session.get(
self.api_url, params=params, headers=headers, timeout=10
) as resp:
if resp.status != 200:
logger.error(f"TTS请求失败: {resp.status}, {await resp.text()}")
self.tts_audio_queue.put((SentenceType.LAST, [], None))
return
self.pcm_buffer.clear()
opus_datas_cache = []
# 兼容 iter_chunked / iter_chunks / iter_any
async for chunk in resp.content.iter_any():
data = chunk[0] if isinstance(chunk, (list, tuple)) else chunk
if not data:
continue
# 拼到 buffer
self.pcm_buffer.extend(data)
# 够一帧就编码
while len(self.pcm_buffer) >= frame_bytes:
frame = bytes(self.pcm_buffer[:frame_bytes])
del self.pcm_buffer[:frame_bytes]
opus = self.opus_encoder.encode_pcm_to_opus(
frame, end_of_stream=False
)
if opus:
if self.segment_count < 10: # 前10个片段直接发送
self.tts_audio_queue.put(
(SentenceType.MIDDLE, opus, text)
)
self.segment_count += 1
else:
opus_datas_cache.extend(opus)
# flush 剩余不足一帧的数据
if self.pcm_buffer:
opus = self.opus_encoder.encode_pcm_to_opus(
bytes(self.pcm_buffer), end_of_stream=True
)
if opus:
if self.segment_count < 10: # 前10个片段直接发送
# 直接发送
self.tts_audio_queue.put(
(SentenceType.MIDDLE, opus, text)
)
self.segment_count += 1
else:
# 后续片段缓存
opus_datas_cache.extend(opus)
self.pcm_buffer.clear()
# 如果不是前10个片段，发送缓存的数据
if self.segment_count >= 10 and opus_datas_cache:
self.tts_audio_queue.put(
(SentenceType.MIDDLE, opus_datas_cache, text)
)
# 如果是最后一段，输出音频获取完毕
if is_last:
self._process_before_stop_play_files()
except Exception as e:
logger.error(f"TTS请求异常: {e}")
self.tts_audio_queue.put((SentenceType.LAST, [], None))