File size: 1,372 Bytes
b231190 88cb1c9 b231190 ded753e b231190 ded753e b231190 ded753e b231190 ded753e 88cb1c9 f815f1f 88cb1c9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
import streamlit as st
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
from gtts import gTTS
import tempfile
import os
# 加载BLIP模型和处理器
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
st.title("图像描述生成器")
st.write("使用摄像头拍照并生成图像的描述。")
# 使用Streamlit的camera_input来获取用户摄像头输入
image_data = st.camera_input("请使用摄像头拍照")
if image_data is not None:
# 将图像数据转换为PIL图像
image = Image.open(image_data)
# 显示拍摄的图像
st.image(image, caption="拍摄的图像", use_column_width=True)
# 生成图像描述
inputs = processor(image, return_tensors="pt")
out = model.generate(**inputs)
caption = processor.decode(out[0], skip_special_tokens=True)
st.write(f"图像描述: {caption}")
# 生成语音
tts = gTTS(text=caption, lang='en')
# 创建临时文件来保存音频
with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as fp:
tts.save(fp.name)
audio_file = fp.name
# 在Streamlit中播放音频
st.audio(audio_file)
# 删除临时文件
os.remove(audio_file)
|