105 lines
3.4 KiB
Python
105 lines
3.4 KiB
Python
|
from llama_cpp import Llama
|
||
|
|
import os
|
||
|
|
from utils.logger import logger
|
||
|
|
|
||
|
|
class Translator:
|
||
|
|
def __init__(self, model_path=None):
|
||
|
|
self.model = None
|
||
|
|
self.model_path = model_path
|
||
|
|
self.is_ready = False
|
||
|
|
self.model_name = ""
|
||
|
|
|
||
|
|
def load_model(self, model_path=None):
|
||
|
|
"""加载模型"""
|
||
|
|
if model_path:
|
||
|
|
self.model_path = model_path
|
||
|
|
|
||
|
|
if not self.model_path:
|
||
|
|
logger.error("未提供模型路径")
|
||
|
|
return False
|
||
|
|
|
||
|
|
if not os.path.exists(self.model_path):
|
||
|
|
logger.error(f"模型文件不存在: {self.model_path}")
|
||
|
|
return False
|
||
|
|
|
||
|
|
try:
|
||
|
|
logger.info(f"开始加载模型: {self.model_path}")
|
||
|
|
self.model = Llama(
|
||
|
|
model_path=self.model_path,
|
||
|
|
n_ctx=2048,
|
||
|
|
n_threads=4,
|
||
|
|
n_gpu_layers=100 # 尽可能使用GPU加速
|
||
|
|
)
|
||
|
|
self.is_ready = True
|
||
|
|
self.model_name = os.path.basename(self.model_path)
|
||
|
|
logger.info(f"模型加载成功: {self.model_name}")
|
||
|
|
return True
|
||
|
|
except Exception as e:
|
||
|
|
logger.error(f"模型加载失败: {e}")
|
||
|
|
self.is_ready = False
|
||
|
|
return False
|
||
|
|
|
||
|
|
def translate(self, text, context="", terms=None):
|
||
|
|
"""执行翻译"""
|
||
|
|
if not self.is_ready or not self.model:
|
||
|
|
logger.error("模型未就绪，无法执行翻译")
|
||
|
|
return ""
|
||
|
|
|
||
|
|
try:
|
||
|
|
# 构建翻译提示词
|
||
|
|
prompt = self._build_prompt(text, context, terms)
|
||
|
|
|
||
|
|
logger.info(f"开始翻译，输入长度: {len(text)} 字符")
|
||
|
|
|
||
|
|
# 调用模型进行翻译
|
||
|
|
output = self.model(
|
||
|
|
prompt,
|
||
|
|
max_tokens=2048,
|
||
|
|
temperature=0.7,
|
||
|
|
top_p=0.95,
|
||
|
|
stop=["\n原文:", "\n译文:", "\n###"]
|
||
|
|
)
|
||
|
|
|
||
|
|
translated_text = output["choices"][0]["text"].strip()
|
||
|
|
logger.info(f"翻译完成，输出长度: {len(translated_text)} 字符")
|
||
|
|
|
||
|
|
return translated_text
|
||
|
|
except Exception as e:
|
||
|
|
logger.error(f"翻译失败: {e}")
|
||
|
|
return ""
|
||
|
|
|
||
|
|
def _build_prompt(self, text, context="", terms=None):
|
||
|
|
"""构建翻译提示词"""
|
||
|
|
prompt = "你是一个专业的翻译助手，根据以下要求将中文翻译成英文：\n"
|
||
|
|
|
||
|
|
if context:
|
||
|
|
prompt += f"\n文本背景/场景介绍：{context}\n"
|
||
|
|
|
||
|
|
if terms:
|
||
|
|
prompt += "\n术语定义：\n"
|
||
|
|
for term in terms:
|
||
|
|
prompt += f"{term}\n"
|
||
|
|
|
||
|
|
prompt += f"\n原文：{text}\n译文："
|
||
|
|
|
||
|
|
return prompt
|
||
|
|
|
||
|
|
def unload_model(self):
|
||
|
|
"""卸载模型"""
|
||
|
|
if self.model:
|
||
|
|
try:
|
||
|
|
del self.model
|
||
|
|
self.model = None
|
||
|
|
self.is_ready = False
|
||
|
|
logger.info("模型已卸载")
|
||
|
|
return True
|
||
|
|
except Exception as e:
|
||
|
|
logger.error(f"模型卸载失败: {e}")
|
||
|
|
return False
|
||
|
|
return True
|
||
|
|
|
||
|
|
def get_model_info(self):
|
||
|
|
"""获取模型信息"""
|
||
|
|
if self.is_ready:
|
||
|
|
return f"{self.model_name.split('.')[0]}"
|
||
|
|
return "未加载模型"
|