update: 音频流式优化

main/xiaozhi-server/core/utils/util.py

@@ -3,10 +3,8 @@ import socket
 import subprocess
 import re
 import os
-import wave
 from io import BytesIO
 from typing import Callable, Any
-
 from core.utils import p3
 import numpy as np
 import requests
@@ -213,23 +211,6 @@ def extract_json_from_string(input_string):
     return None
 
 
-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:
-        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)
-
-    # 获取原始PCM数据（16位小端）
-    raw_data = audio.raw_data
-    return pcm_to_data(raw_data, is_opus)
-
 def audio_to_data_stream(audio_file_path, is_opus=True, callback: Callable[[Any], Any]=None) -> None:
     # 获取文件后缀名
     file_type = os.path.splitext(audio_file_path)[1]
@@ -245,25 +226,9 @@ def audio_to_data_stream(audio_file_path, is_opus=True, callback: Callable[[Any]
 
     # 获取原始PCM数据（16位小端）
     raw_data = audio.raw_data
-    pcm_to_data_stream(raw_data, is_opus,callback)
+    pcm_to_data_stream(raw_data, is_opus, callback)
 
 
-def audio_bytes_to_data(audio_bytes, file_type, is_opus=True):
-    """
-    直接用音频二进制数据转为opus/pcm数据，支持wav、mp3、p3
-    """
-    if file_type == "p3":
-        # 直接用p3解码
-        return p3.decode_opus_from_bytes(audio_bytes)
-    else:
-        # 其他格式用pydub
-        audio = AudioSegment.from_file(
-            BytesIO(audio_bytes), format=file_type, parameters=["-nostdin"]
-        )
-        audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2)
-        raw_data = audio.raw_data
-        return pcm_to_data(raw_data, is_opus)
-
 def audio_bytes_to_data_stream(audio_bytes, file_type, is_opus, callback: Callable[[Any], Any]) -> None:
     """
     直接用音频二进制数据转为opus/pcm数据，支持wav、mp3、p3
@@ -281,37 +246,7 @@ def audio_bytes_to_data_stream(audio_bytes, file_type, is_opus, callback: Callab
         pcm_to_data_stream(raw_data, is_opus, callback)
 
 
-def pcm_to_data(raw_data, is_opus=True):
-    # 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
-
-def pcm_to_data_stream(raw_data, is_opus=True, callback: Callable[[Any], Any]=None):
+def pcm_to_data_stream(raw_data, is_opus=True, callback: Callable[[Any], Any] = None):
     # 初始化Opus编码器
     encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO)
 
@@ -338,32 +273,6 @@ def pcm_to_data_stream(raw_data, is_opus=True, callback: Callable[[Any], Any]=No
             frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk)
             callback(frame_data)
 
-def opus_datas_to_wav_bytes(opus_datas, sample_rate=16000, channels=1):
-    """
-    将opus帧列表解码为wav字节流
-    """
-    decoder = opuslib_next.Decoder(sample_rate, channels)
-    pcm_datas = []
-
-    frame_duration = 60  # ms
-    frame_size = int(sample_rate * frame_duration / 1000)  # 960
-
-    for opus_frame in opus_datas:
-        # 解码为PCM（返回bytes，2字节/采样点）
-        pcm = decoder.decode(opus_frame, frame_size)
-        pcm_datas.append(pcm)
-
-    pcm_bytes = b"".join(pcm_datas)
-
-    # 写入wav字节流
-    wav_buffer = BytesIO()
-    with wave.open(wav_buffer, "wb") as wf:
-        wf.setnchannels(channels)
-        wf.setsampwidth(2)  # 16bit
-        wf.setframerate(sample_rate)
-        wf.writeframes(pcm_bytes)
-    return wav_buffer.getvalue()
-
 
 def check_vad_update(before_config, new_config):
     if (