Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-28 10:03:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

PCM音频模式

Browse Source
This commit is contained in:
玄凤科技
2025-05-06 14:57:29 +08:00
parent 9fc1285c09
commit bde260b330
12 changed files with 66 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/asr/aliyun.py
+1 -14
View File
@@ -158,20 +158,7 @@ class ASRProvider(ASRProviderBase):
request += "&enable_inverse_text_normalization=true"
request += "&enable_voice_detection=false"
return request
def decode_opus(self, opus_data: List[bytes], session_id: str) -> List[bytes]:
"""将Opus数据解码为PCM"""
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
"""PCM数据保存为WAV文件"""
main/xiaozhi-server/core/providers/asr/baidu.py
-16
View File
@@ -49,22 +49,6 @@ class ASRProvider(ASRProviderBase):
return file_path
@staticmethod
def decode_opus(opus_data: List[bytes]) -> bytes:
"""将Opus音频数据解码为PCM数据"""
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
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
+21 -1
View File
@@ -1,6 +1,6 @@
from abc import ABC, abstractmethod
from typing import Optional, Tuple, List
import opuslib_next
from config.logger import setup_logging
TAG = __name__
@@ -17,3 +17,23 @@ class ASRProviderBase(ABC):
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"""
pass
def set_audio_format(self, format: str) -> None:
"""设置音频格式"""
self.audio_format = format
@staticmethod
def decode_opus(opus_data: List[bytes]) -> bytes:
"""将Opus音频数据解码为PCM数据"""
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
main/xiaozhi-server/core/providers/asr/doubao.py
-15
View File
@@ -226,21 +226,6 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).error(f"ASR request failed: {e}", exc_info=True)
return None
@staticmethod
def decode_opus(opus_data: List[bytes], session_id: str) -> List[bytes]:
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
@staticmethod
def slice_data(data: bytes, chunk_size: int) -> (list, bool):
"""
main/xiaozhi-server/core/providers/asr/fun_local.py
+5 -18
View File
@@ -6,9 +6,7 @@ import io
from config.logger import setup_logging
from typing import Optional, Tuple, List
import uuid
import opuslib_next
from core.providers.asr.base import ASRProviderBase
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
@@ -64,27 +62,16 @@ class ASRProvider(ASRProviderBase):
return file_path
@staticmethod
def decode_opus(opus_data: List[bytes], session_id: str) -> List[bytes]:
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
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:
# 合并所有opus数据包
pcm_data = self.decode_opus(opus_data, session_id)
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)
# 判断是否保存为WAV文件
main/xiaozhi-server/core/providers/asr/fun_server.py
-17
View File
@@ -44,23 +44,6 @@ class ASRProvider(ASRProviderBase):
return file_path
@staticmethod
def decode_opus(opus_data: List[bytes]) -> bytes:
"""将Opus音频数据解码为PCM数据"""
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
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
-15
View File
@@ -97,21 +97,6 @@ class ASRProvider(ASRProviderBase):
return file_path
@staticmethod
def decode_opus(opus_data: List[bytes], session_id: str) -> List[bytes]:
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
def read_wave(self, wave_filename: str) -> Tuple[np.ndarray, int]:
"""
Args:
main/xiaozhi-server/core/providers/asr/tencent.py
-16
View File
@@ -45,22 +45,6 @@ class ASRProvider(ASRProviderBase):
return file_path
@staticmethod
def decode_opus(opus_data: List[bytes]) -> bytes:
"""将Opus音频数据解码为PCM数据"""
decoder = opuslib_next.Decoder(16000, 1) # 16kHz, 单声道
pcm_data = []
for opus_packet in opus_data:
try:
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
return pcm_data
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 not opus_data:
main/xiaozhi-server/core/providers/tts/base.py
+18 -7
View File
@@ -53,8 +53,15 @@ class TTSProviderBase(ABC):
async def text_to_speak(self, text, output_file):
pass
def audio_to_pcm_data(self, audio_file_path):
"""音频文件转换为PCM编码"""
return self.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 self.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:
@@ -80,7 +87,7 @@ class TTSProviderBase(ABC):
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
@@ -89,12 +96,16 @@ class TTSProviderBase(ABC):
# 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)
# 转换为numpy数组处理
np_frame = np.frombuffer(chunk, dtype=np.int16)
# 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