mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-28 01:53:53 +08:00
@@ -0,0 +1,24 @@
|
|||||||
|
-- VOSK ASR模型供应器
|
||||||
|
delete from `ai_model_provider` where id = 'SYSTEM_ASR_VoskASR';
|
||||||
|
INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `fields`, `sort`, `creator`, `create_date`, `updater`, `update_date`) VALUES
|
||||||
|
('SYSTEM_ASR_VoskASR', 'ASR', 'vosk', 'VOSK离线语音识别', '[{"key": "model_path", "type": "string", "label": "模型路径"}, {"key": "output_dir", "type": "string", "label": "输出目录"}]', 11, 1, NOW(), 1, NOW());
|
||||||
|
|
||||||
|
-- VOSK ASR模型配置
|
||||||
|
delete from `ai_model_config` where id = 'ASR_VoskASR';
|
||||||
|
INSERT INTO `ai_model_config` VALUES ('ASR_VoskASR', 'ASR', 'VoskASR', 'VOSK离线语音识别', 0, 1, '{\"type\": \"vosk\", \"model_path\": \"\", \"output_dir\": \"tmp/\"}', NULL, NULL, 11, NULL, NULL, NULL, NULL);
|
||||||
|
|
||||||
|
-- 更新VOSK ASR配置说明
|
||||||
|
UPDATE `ai_model_config` SET
|
||||||
|
`doc_link` = 'https://alphacephei.com/vosk/',
|
||||||
|
`remark` = 'VOSK ASR配置说明:
|
||||||
|
1. VOSK是一个离线语音识别库,支持多种语言
|
||||||
|
2. 需要先下载模型文件:https://alphacephei.com/vosk/models
|
||||||
|
3. 中文模型推荐使用vosk-model-small-cn-0.22或vosk-model-cn-0.22
|
||||||
|
4. 完全离线运行,无需网络连接
|
||||||
|
5. 输出文件保存在tmp/目录
|
||||||
|
使用步骤:
|
||||||
|
1. 访问 https://alphacephei.com/vosk/models 下载中文模型
|
||||||
|
2. 解压模型文件到项目目录下的models/vosk/文件夹
|
||||||
|
3. 在配置中指定正确的模型路径
|
||||||
|
4. 注意:VOSK中文模型输出不带标点符号,词与词之间会有空格
|
||||||
|
' WHERE `id` = 'ASR_VoskASR';
|
||||||
@@ -303,3 +303,10 @@ databaseChangeLog:
|
|||||||
- sqlFile:
|
- sqlFile:
|
||||||
encoding: utf8
|
encoding: utf8
|
||||||
path: classpath:db/changelog/202508131557.sql
|
path: classpath:db/changelog/202508131557.sql
|
||||||
|
- changeSet:
|
||||||
|
id: 202508271113
|
||||||
|
author: cgd
|
||||||
|
changes:
|
||||||
|
- sqlFile:
|
||||||
|
encoding: utf8
|
||||||
|
path: classpath:db/changelog/202508271113.sql
|
||||||
|
|||||||
@@ -392,6 +392,22 @@ ASR:
|
|||||||
base_url: https://api.groq.com/openai/v1/audio/transcriptions
|
base_url: https://api.groq.com/openai/v1/audio/transcriptions
|
||||||
model_name: whisper-large-v3-turbo
|
model_name: whisper-large-v3-turbo
|
||||||
output_dir: tmp/
|
output_dir: tmp/
|
||||||
|
VoskASR:
|
||||||
|
# 官方网站:https://alphacephei.com/vosk/
|
||||||
|
# 配置说明:
|
||||||
|
# 1. VOSK是一个离线语音识别库,支持多种语言
|
||||||
|
# 2. 需要先下载模型文件:https://alphacephei.com/vosk/models
|
||||||
|
# 3. 中文模型推荐使用vosk-model-small-cn-0.22或vosk-model-cn-0.22
|
||||||
|
# 4. 完全离线运行,无需网络连接
|
||||||
|
# 5. 输出文件保存在tmp/目录
|
||||||
|
# 使用步骤:
|
||||||
|
# 1. 访问 https://alphacephei.com/vosk/models 下载对应的模型
|
||||||
|
# 2. 解压模型文件到项目目录下的models/vosk/文件夹
|
||||||
|
# 3. 在配置中指定正确的模型路径
|
||||||
|
# 4. 注意:VOSK中文模型输出不带标点符号,词与词之间会有空格
|
||||||
|
type: vosk
|
||||||
|
model_path: 你的模型路径,如:models/vosk/vosk-model-small-cn-0.22
|
||||||
|
output_dir: tmp/
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,114 @@
|
|||||||
|
import os
|
||||||
|
import json
|
||||||
|
import time
|
||||||
|
from typing import Optional, Tuple, List
|
||||||
|
from .base import ASRProviderBase
|
||||||
|
from config.logger import setup_logging
|
||||||
|
from core.providers.asr.dto.dto import InterfaceType
|
||||||
|
import vosk
|
||||||
|
|
||||||
|
TAG = __name__
|
||||||
|
logger = setup_logging()
|
||||||
|
|
||||||
|
class ASRProvider(ASRProviderBase):
|
||||||
|
def __init__(self, config: dict, delete_audio_file: bool = True):
|
||||||
|
super().__init__()
|
||||||
|
self.interface_type = InterfaceType.LOCAL
|
||||||
|
self.model_path = config.get("model_path")
|
||||||
|
self.output_dir = config.get("output_dir", "tmp/")
|
||||||
|
self.delete_audio_file = delete_audio_file
|
||||||
|
|
||||||
|
# 初始化VOSK模型
|
||||||
|
self.model = None
|
||||||
|
self.recognizer = None
|
||||||
|
self._load_model()
|
||||||
|
|
||||||
|
# 确保输出目录存在
|
||||||
|
os.makedirs(self.output_dir, exist_ok=True)
|
||||||
|
|
||||||
|
def _load_model(self):
|
||||||
|
"""加载VOSK模型"""
|
||||||
|
try:
|
||||||
|
if not os.path.exists(self.model_path):
|
||||||
|
raise FileNotFoundError(f"VOSK模型路径不存在: {self.model_path}")
|
||||||
|
|
||||||
|
logger.bind(tag=TAG).info(f"正在加载VOSK模型: {self.model_path}")
|
||||||
|
self.model = vosk.Model(self.model_path)
|
||||||
|
|
||||||
|
# 初始化VOSK识别器(采样率必须为16kHz)
|
||||||
|
self.recognizer = vosk.KaldiRecognizer(self.model, 16000)
|
||||||
|
|
||||||
|
logger.bind(tag=TAG).info("VOSK模型加载成功")
|
||||||
|
except Exception as e:
|
||||||
|
logger.bind(tag=TAG).error(f"加载VOSK模型失败: {e}")
|
||||||
|
raise
|
||||||
|
|
||||||
|
async def speech_to_text(
|
||||||
|
self, audio_data: List[bytes], session_id: str, audio_format: str = "opus"
|
||||||
|
) -> Tuple[Optional[str], Optional[str]]:
|
||||||
|
"""将语音数据转换为文本"""
|
||||||
|
file_path = None
|
||||||
|
try:
|
||||||
|
# 检查模型是否加载成功
|
||||||
|
if not self.model:
|
||||||
|
logger.bind(tag=TAG).error("VOSK模型未加载,无法进行识别")
|
||||||
|
return "", None
|
||||||
|
|
||||||
|
# 解码音频(如果原始格式是Opus)
|
||||||
|
if audio_format == "pcm":
|
||||||
|
pcm_data = audio_data
|
||||||
|
else:
|
||||||
|
pcm_data = self.decode_opus(audio_data)
|
||||||
|
|
||||||
|
if not pcm_data:
|
||||||
|
logger.bind(tag=TAG).warning("解码后的PCM数据为空,无法进行识别")
|
||||||
|
return "", None
|
||||||
|
|
||||||
|
# 合并PCM数据
|
||||||
|
combined_pcm_data = b"".join(pcm_data)
|
||||||
|
if len(combined_pcm_data) == 0:
|
||||||
|
logger.bind(tag=TAG).warning("合并后的PCM数据为空")
|
||||||
|
return "", None
|
||||||
|
|
||||||
|
# 判断是否保存为WAV文件
|
||||||
|
if not self.delete_audio_file:
|
||||||
|
file_path = self.save_audio_to_file(pcm_data, session_id)
|
||||||
|
|
||||||
|
start_time = time.time()
|
||||||
|
|
||||||
|
|
||||||
|
# 进行识别(VOSK推荐每次送入2000字节的数据)
|
||||||
|
chunk_size = 2000
|
||||||
|
text_result = ""
|
||||||
|
|
||||||
|
for i in range(0, len(combined_pcm_data), chunk_size):
|
||||||
|
chunk = combined_pcm_data[i:i+chunk_size]
|
||||||
|
if self.recognizer.AcceptWaveform(chunk):
|
||||||
|
result = json.loads(self.recognizer.Result())
|
||||||
|
text = result.get('text', '')
|
||||||
|
if text:
|
||||||
|
text_result += text + " "
|
||||||
|
|
||||||
|
# 获取最终结果
|
||||||
|
final_result = json.loads(self.recognizer.FinalResult())
|
||||||
|
final_text = final_result.get('text', '')
|
||||||
|
if final_text:
|
||||||
|
text_result += final_text
|
||||||
|
|
||||||
|
logger.bind(tag=TAG).debug(
|
||||||
|
f"VOSK语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text_result.strip()}"
|
||||||
|
)
|
||||||
|
|
||||||
|
return text_result.strip(), file_path
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
logger.bind(tag=TAG).error(f"VOSK语音识别失败: {e}")
|
||||||
|
return "", None
|
||||||
|
finally:
|
||||||
|
# 文件清理逻辑
|
||||||
|
if self.delete_audio_file and file_path and os.path.exists(file_path):
|
||||||
|
try:
|
||||||
|
os.remove(file_path)
|
||||||
|
logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
|
||||||
|
except Exception as e:
|
||||||
|
logger.bind(tag=TAG).error(f"文件删除失败: {file_path} | 错误: {e}")
|
||||||
Reference in New Issue
Block a user