Music play (#142)

* Update util.py解决返回元组报错 (#103) 解决返回元组报错 * 增加播放本地音乐功能 (#105) * Please enter the commit message for your changes. Lines starting with '#' will be ignored, and an empty message aborts the commit. On branch Music-playback Your branch is up to date with 'origin/Music-playback'. Changes to be committed: modified: core/handle/audioHandle.py new file: "music/\346\234\210\344\272\256\344\273\243\350\241\250\346\210\221\347\232\204\345\277\203_\351\202\223\344\270\275\345\220\233.mp3" new file: "music/\350\270\217\345\261\261\346\262\263.mp3" * Please enter the commit message for your changes. Lines starting with '#' will be ignored, and an empty message aborts the commit. On branch Music-playback Your branch is up to date with 'origin/Music-playback'. Changes to be committed: modified: config.yaml modified: core/connection.py modified: core/handle/abortHandle.py modified: core/handle/audioHandle.py new file: core/handle/musicHandler.py modified: core/handle/textHandle.py modified: core/websocket_server.py new file: "music/\344\270\200\345\277\265\345\215\203\345\271\264_\345\233\275\351\243\216\347\211\210.mp3" new file: "music/\344\270\255\347\247\213\346\234\210.mp3" deleted: "music/\346\234\210\344\272\256\344\273\243\350\241\250\346\210\221\347\232\204\345\277\203_\351\202\223\344\270\275\345\220\233.mp3" deleted: "music/\350\270\217\345\261\261\346\262\263.mp3" * 增加播放本地音乐功能 * 增加播放本地音乐功能 * 让音乐配置变的优雅 On branch Music-playback Your branch is up to date with 'origin/Music-playback'. Changes to be committed: modified: config.yaml modified: core/handle/musicHandler.py renamed: "music/\344\270\200\345\277\265\345\215\203\345\271\264_\345\233\275\351\243\216\347\211\210.mp3" -> "music/mp3/\344\270\200\345\277\265\345\215\203\345\271\264_\345\233\275\351\243\216\347\211\210.mp3" renamed: "music/\344\270\255\347\247\213\346\234\210.mp3" -> "music/mp3/\344\270\255\347\247\213\346\234\210.mp3" renamed: "music/\345\273\211\346\263\242\350\200\201\347\237\243\357\274\214\345\260\232\350\203\275\351\245\255\345\220\246.mp3" -> "music/mp3/\345\273\211\346\263\242\350\200\201\347\237\243\357\274\214\345\260\232\350\203\275\351\245\255\345\220\246.mp3" new file: music/music_config.yaml --------- Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com> * update:优化代码 * update:流控调试 * update:优化音乐播放 * update:优化音乐配置初始化 --------- Co-authored-by: linqingping <linqingping@users.noreply.github.com> Co-authored-by: Chris <119588753+Chris-websketch@users.noreply.github.com> Co-authored-by: hrz <1710360675@qq.com>
2026-07-26 00:53:54 +08:00 · 2025-02-26 01:33:05 +08:00
parent 73803f49fc
commit 87cb0b484d
11 changed files with 242 additions and 94 deletions
@@ -0,0 +1,109 @@
+from config.logger import setup_logging
+import os
+import random
+import difflib
+import re
+import traceback
+from core.handle.sendAudioHandle import sendAudioMessage, send_stt_message
+
+TAG = __name__
+logger = setup_logging()
+
+
+def _extract_song_name(text):
+    """从用户输入中提取歌名"""
+    for keyword in ["听", "播放", "放", "唱"]:
+        if keyword in text:
+            parts = text.split(keyword)
+            if len(parts) > 1:
+                return parts[1].strip()
+    return None
+
+
+def _find_best_match(potential_song, music_files):
+    """查找最匹配的歌曲"""
+    best_match = None
+    highest_ratio = 0
+
+    for music_file in music_files:
+        song_name = os.path.splitext(music_file)[0]
+        ratio = difflib.SequenceMatcher(None, potential_song, song_name).ratio()
+        if ratio > highest_ratio and ratio > 0.4:
+            highest_ratio = ratio
+            best_match = music_file
+    return best_match
+
+
+class MusicHandler:
+    def __init__(self, config):
+        self.config = config
+        self.music_related_keywords = []
+
+        if "music" in self.config:
+            self.music_config = self.config["music"]
+            self.music_dir = os.path.abspath(
+                self.music_config.get("music_dir", "./music")  # 默认路径修改
+            )
+            self.music_related_keywords = self.music_config.get("music_commands", [])
+        else:
+            self.music_dir = os.path.abspath("./music")
+            self.music_related_keywords = ["来一首歌", "唱一首歌", "播放音乐", "来点音乐", "背景音乐", "放首歌",
+                                           "播放歌曲", "来点背景音乐", "我想听歌", "我要听歌", "放点音乐"]
+
+    async def handle_music_command(self, conn, text):
+        """处理音乐播放指令"""
+        clean_text = re.sub(r'[^\w\s]', '', text).strip()
+        logger.bind(tag=TAG).debug(f"检查是否是音乐命令: {clean_text}")
+
+        # 尝试匹配具体歌名
+        if os.path.exists(self.music_dir):
+            music_files = [f for f in os.listdir(self.music_dir) if f.endswith('.mp3')]
+            logger.bind(tag=TAG).debug(f"找到的音乐文件: {music_files}")
+
+            potential_song = _extract_song_name(clean_text)
+            if potential_song:
+                best_match = _find_best_match(potential_song, music_files)
+                if best_match:
+                    logger.bind(tag=TAG).info(f"找到最匹配的歌曲: {best_match}")
+                    await self.play_local_music(conn, specific_file=best_match)
+                    return True
+
+        # 检查是否是通用播放音乐命令
+        if any(cmd in clean_text for cmd in self.music_related_keywords):
+            await self.play_local_music(conn)
+            return True
+
+        return False
+
+    async def play_local_music(self, conn, specific_file=None):
+        """播放本地音乐文件"""
+        try:
+            if not os.path.exists(self.music_dir):
+                logger.bind(tag=TAG).error(f"音乐目录不存在: {self.music_dir}")
+                return
+
+            # 确保路径正确性
+            if specific_file:
+                music_path = os.path.join(self.music_dir, specific_file)
+                if not os.path.exists(music_path):
+                    logger.bind(tag=TAG).error(f"指定的音乐文件不存在: {music_path}")
+                    return
+                selected_music = specific_file
+            else:
+                music_files = [f for f in os.listdir(self.music_dir) if f.endswith('.mp3')]
+                if not music_files:
+                    logger.bind(tag=TAG).error("未找到MP3音乐文件")
+                    return
+                selected_music = random.choice(music_files)
+                music_path = os.path.join(self.music_dir, selected_music)
+            text = f"正在播放{selected_music}"
+            await send_stt_message(conn, text)
+            conn.tts_first_text = selected_music
+            conn.tts_last_text = selected_music
+            conn.llm_finish_task = True
+            opus_packets, duration = conn.tts.wav_to_opus_data(music_path)
+            await sendAudioMessage(conn, opus_packets, duration, selected_music)
+
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")
+            logger.bind(tag=TAG).error(f"详细错误: {traceback.format_exc()}")
@@ -0,0 +1,81 @@
+from config.logger import setup_logging
+import asyncio
+import time
+from core.utils.util import remove_punctuation_and_length
+from core.handle.sendAudioHandle import schedule_with_interrupt, send_stt_message
+
+TAG = __name__
+logger = setup_logging()
+
+
+async def handleAudioMessage(conn, audio):
+    if not conn.asr_server_receive:
+        logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
+        return
+    if conn.client_listen_mode == "auto":
+        have_voice = conn.vad.is_vad(conn, audio)
+    else:
+        have_voice = conn.client_have_voice
+
+    # 如果本次没有声音，本段也没声音，就把声音丢弃了
+    if have_voice == False and conn.client_have_voice == False:
+        await no_voice_close_connect(conn)
+        conn.asr_audio.clear()
+        return
+    conn.client_no_voice_last_time = 0.0
+    conn.asr_audio.append(audio)
+    # 如果本段有声音，且已经停止了
+    if conn.client_voice_stop:
+        conn.client_abort = False
+        conn.asr_server_receive = False
+        # 音频太短了，无法识别
+        if len(conn.asr_audio) < 3:
+            conn.asr_server_receive = True
+        else:
+            text, file_path = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
+            logger.bind(tag=TAG).info(f"识别文本: {text}")
+            text_len, text_without_punctuation = remove_punctuation_and_length(text)
+            if await conn.music_handler.handle_music_command(conn, text_without_punctuation):
+                conn.asr_server_receive = True
+                conn.asr_audio.clear()
+                return
+            if text_len <= conn.max_cmd_length and await handleCMDMessage(conn, text_without_punctuation):
+                return
+            if text_len > 0:
+                await startToChat(conn, text)
+            else:
+                conn.asr_server_receive = True
+        conn.asr_audio.clear()
+        conn.reset_vad_states()
+
+
+async def handleCMDMessage(conn, text):
+    cmd_exit = conn.cmd_exit
+    for cmd in cmd_exit:
+        if text == cmd:
+            logger.bind(tag=TAG).info("识别到明确的退出命令".format(text))
+            await conn.close()
+            return True
+    return False
+
+
+async def startToChat(conn, text):
+    # 异步发送 stt 信息
+    stt_task = asyncio.create_task(
+        schedule_with_interrupt(0, send_stt_message(conn, text))
+    )
+    conn.scheduled_tasks.append(stt_task)
+    conn.executor.submit(conn.chat, text)
+
+
+async def no_voice_close_connect(conn):
+    if conn.client_no_voice_last_time == 0.0:
+        conn.client_no_voice_last_time = time.time() * 1000
+    else:
+        no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
+        close_connection_no_voice_time = conn.config.get("close_connection_no_voice_time", 120)
+        if no_voice_time > 1000 * close_connection_no_voice_time:
+            conn.client_abort = False
+            conn.asr_server_receive = False
+            prompt = "时间过得真快，我都好久没说话了。请你用十个字左右话跟我告别，以“再见”或“拜拜”为结尾"
+            await startToChat(conn, prompt)
@@ -8,56 +8,6 @@ TAG = __name__
 logger = setup_logging()


-async def handleAudioMessage(conn, audio):
-    if not conn.asr_server_receive:
-        logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
-        return
-    if conn.client_listen_mode == "auto":
-        have_voice = conn.vad.is_vad(conn, audio)
-    else:
-        have_voice = conn.client_have_voice
-
-    # 如果本次没有声音，本段也没声音，就把声音丢弃了
-    if have_voice == False and conn.client_have_voice == False:
-        await no_voice_close_connect(conn)
-        conn.asr_audio.clear()
-        return
-    conn.client_no_voice_last_time = 0.0
-    conn.asr_audio.append(audio)
-    # 如果本段有声音，且已经停止了
-    if conn.client_voice_stop:
-        conn.client_abort = False
-        conn.asr_server_receive = False
-        # 音频太短了，无法识别
-        if len(conn.asr_audio) < 3:
-            conn.asr_server_receive = True
-        else:
-            text, file_path = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
-            logger.bind(tag=TAG).info(f"识别文本: {text}")
-            text_len, text_without_punctuation = remove_punctuation_and_length(text)
-            if text_len <= conn.max_cmd_length and await handleCMDMessage(conn, text_without_punctuation):
-                return
-            if text_len > 0:
-                await startToChat(conn, text)
-            else:
-                conn.asr_server_receive = True
-        conn.asr_audio.clear()
-        conn.reset_vad_states()
-
-async def handleCMDMessage(conn, text):
-    cmd_exit = conn.cmd_exit
-    for cmd in cmd_exit:
-        if text == cmd:
-            logger.bind(tag=TAG).info("识别到明确的退出命令".format(text))
-            await finishToChat(conn)
-            return True
-    return False
-
-
-async def finishToChat(conn):
-    await conn.close()
-
-
 async def isLLMWantToFinish(conn):
    first_text = conn.tts_first_text
    last_text = conn.tts_last_text
@@ -70,15 +20,6 @@ async def isLLMWantToFinish(conn):
    return False


-async def startToChat(conn, text):
-    # 异步发送 stt 信息
-    stt_task = asyncio.create_task(
-        schedule_with_interrupt(0, send_stt_message(conn, text))
-    )
-    conn.scheduled_tasks.append(stt_task)
-    conn.executor.submit(conn.chat, text)
-
-
 async def sendAudioMessage(conn, audios, duration, text):
    base_delay = conn.tts_duration

@@ -107,7 +48,7 @@ async def sendAudioMessage(conn, audios, duration, text):
        conn.scheduled_tasks.append(stop_task)
        if await isLLMWantToFinish(conn):
            finish_task = asyncio.create_task(
-                schedule_with_interrupt(stop_duration, finishToChat(conn))
+                schedule_with_interrupt(stop_duration, await conn.close())
            )
            conn.scheduled_tasks.append(finish_task)

@@ -152,16 +93,3 @@ async def schedule_with_interrupt(delay, coro):
        await coro
    except asyncio.CancelledError:
        pass
-
-
-async def no_voice_close_connect(conn):
-    if conn.client_no_voice_last_time == 0.0:
-        conn.client_no_voice_last_time = time.time() * 1000
-    else:
-        no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
-        close_connection_no_voice_time = conn.config.get("close_connection_no_voice_time", 120)
-        if no_voice_time > 1000 * close_connection_no_voice_time:
-            conn.client_abort = False
-            conn.asr_server_receive = False
-            prompt = "时间过得真快，我都好久没说话了。请你用十个字左右话跟我告别，以“再见”或“拜拜”为结尾"
-            await startToChat(conn, prompt)
@@ -2,7 +2,7 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
-from core.handle.audioHandle import startToChat
+from core.handle.receiveAudioHandle import startToChat
 from core.handle.iotHandle import handleIotDescriptors

 TAG = __name__
@@ -39,7 +39,6 @@ async def handleTextMessage(conn, message):
                    await startToChat(conn, msg_json["text"])
        elif msg_json["type"] == "iot":
            if "descriptors" in msg_json:
-                pass
-                # await handleIotDescriptors(conn, msg_json["descriptors"])
+                await handleIotDescriptors(conn, msg_json["descriptors"])
    except json.JSONDecodeError:
        await conn.websocket.send(message)