mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-26 00:53:54 +08:00
update:audio_to_data改成异步方法
This commit is contained in:
@@ -4,6 +4,7 @@ import json
|
||||
import copy
|
||||
import wave
|
||||
import socket
|
||||
import asyncio
|
||||
import requests
|
||||
import subprocess
|
||||
import numpy as np
|
||||
@@ -268,56 +269,62 @@ def audio_to_data_stream(
|
||||
pcm_to_data_stream(raw_data, is_opus, callback)
|
||||
|
||||
|
||||
def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[bytes]:
|
||||
async def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[bytes]:
|
||||
"""
|
||||
将音频文件转换为Opus/PCM编码的帧列表
|
||||
Args:
|
||||
audio_file_path: 音频文件路径
|
||||
is_opus: 是否进行Opus编码
|
||||
"""
|
||||
# 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)
|
||||
def _sync_audio_to_data():
|
||||
# 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"]
|
||||
)
|
||||
|
||||
# 获取原始PCM数据(16位小端)
|
||||
raw_data = audio.raw_data
|
||||
# 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)
|
||||
|
||||
# 初始化Opus编码器
|
||||
encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO)
|
||||
# 获取原始PCM数据(16位小端)
|
||||
raw_data = audio.raw_data
|
||||
|
||||
# 编码参数
|
||||
frame_duration = 60 # 60ms per frame
|
||||
frame_size = int(16000 * frame_duration / 1000) # 960 samples/frame
|
||||
# 初始化Opus编码器
|
||||
encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO)
|
||||
|
||||
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]
|
||||
# 编码参数
|
||||
frame_duration = 60 # 60ms per frame
|
||||
frame_size = int(16000 * frame_duration / 1000) # 960 samples/frame
|
||||
|
||||
# 如果最后一帧不足,补零
|
||||
if len(chunk) < frame_size * 2:
|
||||
chunk += b"\x00" * (frame_size * 2 - len(chunk))
|
||||
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]
|
||||
|
||||
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)
|
||||
# 如果最后一帧不足,补零
|
||||
if len(chunk) < frame_size * 2:
|
||||
chunk += b"\x00" * (frame_size * 2 - len(chunk))
|
||||
|
||||
datas.append(frame_data)
|
||||
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)
|
||||
|
||||
return datas
|
||||
datas.append(frame_data)
|
||||
|
||||
return datas
|
||||
|
||||
loop = asyncio.get_running_loop()
|
||||
# 在单独的线程中执行同步的音频处理操作
|
||||
return await loop.run_in_executor(None, _sync_audio_to_data)
|
||||
|
||||
|
||||
def audio_bytes_to_data_stream(
|
||||
|
||||
Reference in New Issue
Block a user