Upload folder using huggingface_hub

README.md

@@ -1,12 +1,6 @@
 ---
-title: RoboAssist Demo
-emoji: 🏢
-colorFrom: green
-colorTo: gray
+title: roboAssist_demo
+app_file: web_demo_audio.py
 sdk: gradio
-sdk_version: 4.44.0
-app_file: app.py
-pinned: false
+sdk_version: 4.31.3
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

cert.pem

@@ -0,0 +1,35 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----

demo.sh

@@ -0,0 +1,14 @@
+echo $CUDA_VISIBLE_DEVICES
+SERVER_PORT=9001
+MASTER_ADDR=localhost
+MASTER_PORT="3${SERVER_PORT}"
+NNODES=${WORLD_SIZE:-1}
+NODE_RANK=${RANK:-0}
+GPUS_PER_NODE=1
+python -m torch.distributed.launch --use_env \
+     --nproc_per_node $GPUS_PER_NODE  --nnodes $NNODES \
+     --node_rank $NODE_RANK \
+     --master_addr=${MASTER_ADDR:-127.0.0.1} \
+     --master_port=$MASTER_PORT \
+     web_demo_audio.py \
+     --server-port ${SERVER_PORT}

key.pem

@@ -0,0 +1,52 @@
+-----BEGIN PRIVATE KEY-----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+-----END PRIVATE KEY-----

my_code.py

@@ -0,0 +1 @@
+from langchain_community.document_loaders import JSONLoader

requirements_web_demo.txt

@@ -0,0 +1,2 @@
+gradio==4.31.3
+modelscope-studio

test_audio.py

@@ -0,0 +1,295 @@
+import gradio as gr
+import modelscope_studio as mgr
+import librosa
+from transformers import AutoProcessor, Qwen2AudioForConditionalGeneration
+from argparse import ArgumentParser
+import requests
+import os
+from django.http import HttpResponse
+
+# 默认的模型检查点路径
+DEFAULT_CKPT_PATH = 'Qwen/Qwen2-Audio-7B-Instruct'
+
+def text_to_speech(text2):
+    data = {
+        "text": text2,
+        "text_language": "zh",
+    }
+    # 注意 URL 中的单引号应该是 URL 的一部分，需要正确转义
+    response = requests.post('http://127.0.0.1:8000', json=data)
+    
+    if response.status_code == 200:
+        audio_file_path = "/root/project/Qwen2-Audio/demo/output.mp3"
+        with open(audio_file_path, "wb") as f:
+            f.write(response.content)
+        return audio_file_path
+    else:
+        print(f"错误：请求失败，状态码为 {response.status_code}")
+        return None
+
+def _get_args():
+    """
+    解析命令行参数，获取运行配置。
+
+    返回:
+        argparse.Namespace: 包含命令行参数的命名空间对象。
+    """
+    parser = ArgumentParser()
+    parser.add_argument("-c", "--checkpoint-path", type=str, default=DEFAULT_CKPT_PATH,
+                        help="Checkpoint name or path, default to %(default)r")  # 模型检查点路径
+    parser.add_argument("--cpu-only", action="store_true", help="Run demo with CPU only")  # 是否仅使用CPU
+    parser.add_argument("--inbrowser", action="store_true", default=False,
+                        help="Automatically launch the interface in a new tab on the default browser.")  # 是否在浏览器中自动打开界面
+    parser.add_argument("--server-port", type=int, default=15110,
+                        help="Demo server port.")  # 指定服务器端口
+    parser.add_argument("--server-name", type=str, default="0.0.0.0",
+                        help="Demo server name.")  # 指定服务器名称
+
+    args = parser.parse_args()
+    return args
+
+def add_text(chatbot, task_history, input):
+    """
+    将用户输入的文本内容添加到聊天记录中，并更新聊天机器人界面。
+
+    参数:
+        chatbot (gr.components.Chatbot): 聊天机器人组件。
+        task_history (list): 任务历史记录。
+        input (gr.inputs): 用户输入内容。
+
+    返回:
+        tuple: 更新后的聊天机器人界面和任务历史记录，以及重置后的用户输入框。
+    """
+    text_content = input.text  # 获取文本输入内容
+    content = []
+    if len(input.files) > 0:  # 如果用户上传了音频文件
+        for i in input.files:
+            content.append({'type': 'audio', 'audio_url': i.path})  # 将音频文件添加到内容列表中
+    if text_content:  # 如果用户输入了文本
+        content.append({'type': 'text', 'text': text_content})  # 将文本内容添加到内容列表中
+    task_history.append({"role": "user", "content": content})  # 更新任务历史记录
+
+    # 更新聊天机器人界面，添加用户输入
+    chatbot.append([{
+        "text": input.text,
+        "files": input.files,
+    }, None])
+    return chatbot, task_history, None
+'''
+def add_file(chatbot, task_history, audio_file_path):
+    """
+    将音频文件添加到聊天记录中。
+
+    参数:
+        chatbot (gr.components.Chatbot): 聊天机器人组件。
+        task_history (list): 任务历史记录。
+        audio_file_path (str): 音频文件的路径。
+
+    返回:
+        tuple: 更新后的聊天机器人界面和任务历史记录。
+    """
+    # 确保任务历史记录中的音频条目是正确的格式
+    task_history.append({"role": "user", "content": [{"type": "audio", "audio_url": audio_file_path}]})
+    
+    # 更新聊天记录，直接使用 audio_file_path 而不是 gr.Audio 组件
+    chatbot.append((None, {"type": "audio", "audio_url": audio_file_path}))
+
+    return chatbot, task_history
+'''
+import os
+
+def add_file(chatbot, task_history, audio_path):
+    if not os.path.isfile(audio_path):
+        print(f"Error: The file {audio_path} does not exist.")
+        return chatbot, task_history
+
+    # 将音频文件信息添加到任务历史
+    task_history.append({
+        "role": "user",
+        "content": [{"type": "audio", "audio_url": audio_path}]
+    })
+
+    # 假设 chatbot 组件可以接受字典格式的输入
+    chatbot_state = [{
+        "text": f"[Audio file: {os.path.basename(audio_path)}]",
+        "files": [audio_path]  # 直接使用文件路径而不是 gr.File
+    }, None]
+    chatbot.append(chatbot_state)  # 更新 chatbot 状态
+
+    return chatbot, task_history
+
+def reset_user_input():
+    """
+    重置用户输入字段。
+
+    返回:
+        gr.update: 将文本框的值重置为空。
+    """
+    return gr.Textbox.update(value='')
+
+def reset_state(task_history):
+    """
+    重置聊天记录和任务历史。
+
+    参数:
+        task_history (list): 当前的任务历史记录。
+
+    返回:
+        tuple: 清空的聊天记录和任务历史。
+    """
+    return [], []
+
+def regenerate(chatbot, task_history):
+    """
+    重新生成最后的机器人响应。
+
+    参数:
+        chatbot (gr.components.Chatbot): 聊天机器人组件。
+        task_history (list): 任务历史记录。
+
+    返回:
+        tuple: 更新后的聊天机器人界面和任务历史记录。
+    """
+    # 如果最后一条消息是助手生成的，则移除它
+    if task_history and task_history[-1]['role'] == 'assistant':
+        task_history.pop()
+        chatbot.pop()
+    # 如果任务历史记录不为空，重新生成响应
+    if task_history:
+        chatbot, task_history = predict(chatbot, task_history)
+    return chatbot, task_history
+
+def predict(chatbot, task_history):
+    """
+    根据当前任务历史记录生成模型响应，并将响应转换为音频文件添加到聊天记录中。
+
+    参数:
+        chatbot (gr.components.Chatbot): 聊天机器人组件。
+        task_history (list): 任务历史记录。
+
+    返回:
+        tuple: 更新后的聊天机器人界面和任务历史记录。
+    """
+    print(f"{task_history=}")
+    print(f"{chatbot=}")
+
+    # 使用处理器将任务历史记录格式化为模型输入
+    text = processor.apply_chat_template(task_history, add_generation_prompt=True, tokenize=False)
+    audios = []
+
+    # 遍历任务历史，查找音频内容并加载
+    for message in task_history:
+        if isinstance(message["content"], list):
+            for ele in message["content"]:
+                if ele["type"] == "audio":
+                    audios.append(
+                        librosa.load(ele['audio_url'], sr=processor.feature_extractor.sampling_rate)[0]
+                    )
+
+    if len(audios) == 0:  # 如果没有音频，则设置为 None
+        audios = None
+    print(f"{text=}")
+    print(f"{audios=}")
+
+    # 使用处理器生成模型输入
+    inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
+    if not _get_args().cpu_only:  # 如果支持 GPU，则将输入数据移动到 CUDA 设备
+        inputs["input_ids"] = inputs.input_ids.to("cuda")
+
+    # 生成响应
+    generate_ids = model.generate(**inputs, max_length=256)
+    generate_ids = generate_ids[:, inputs.input_ids.size(1):]
+
+    # 解码生成的文本响应
+    # 假设其他参数已经正确设置
+    response = processor.batch_decode(generate_ids, skip_special_tokens=True)[0]
+    task_history.append({'role': 'assistant', 'content': response})
+    chatbot.append((None, response))  # 添加文本响应
+
+    # 将文本响应转换为语音
+    audio_file_path = text_to_speech(response)
+    if audio_file_path:
+        chatbot, task_history = add_file(chatbot, task_history, audio_file_path)
+
+    return chatbot, task_history
+
+def _launch_demo(args):
+    """
+    启动Gradio的Web用户界面，展示Qwen2-Audio-Instruct模型的聊天功能。
+
+    参数:
+        args (argparse.Namespace): 从命令行解析的参数。
+    """
+    with gr.Blocks() as demo:
+        # 添加页面标题和描述
+        gr.Markdown(
+            """<p align="center"><img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/assets/blog/qwenaudio/qwen2audio_logo.png" style="height: 80px"/><p>""")
+        gr.Markdown("""<center><font size=8>Qwen2-Audio-Instruct Bot</center>""")
+        gr.Markdown(
+            """\
+    <center><font size=3>This WebUI is based on Qwen2-Audio-Instruct, developed by Alibaba Cloud. \
+    (本WebUI基于Qwen2-Audio-Instruct打造，实现聊天机器人功能。)</center>""")
+        gr.Markdown("""\
+    <center><font size=4>Qwen2-Audio <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B">🤖 </a> 
+    | <a href="https://huggingface.co/Qwen/Qwen2-Audio-7B">🤗</a>&nbsp ｜ 
+    Qwen2-Audio-Instruct <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B-Instruct">🤖 </a> | 
+    <a href="https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct">🤗</a>&nbsp ｜ 
+    &nbsp<a href="https://github.com/QwenLM/Qwen2-Audio">Github</a></center>""")
+        
+        # 创建聊天机器人组件
+        chatbot = mgr.Chatbot(label='Qwen2-Audio-7B-Instruct', elem_classes="control-height", height=750)
+
+        # 创建用户输入组件，支持文本、麦克风和文件上传
+        user_input = mgr.MultimodalInput(
+            interactive=True,
+            sources=['microphone', 'upload'],
+            submit_button_props=dict(value="🚀 Submit (发送)"),
+            upload_button_props=dict(value="📁 Upload (上传文件)", show_progress=True),
+        )
+        task_history = gr.State([])  # 初始化任务历史状态
+
+        with gr.Row():  # 创建清除历史和重试按钮
+            empty_bin = gr.Button("🧹 Clear History (清除历史)")
+            regen_btn = gr.Button("🤔️ Regenerate (重试)")
+
+        # 当用户提交输入时，调用add_text函数，然后调用predict函数生成响应
+        user_input.submit(fn=add_text,
+                          inputs=[chatbot, task_history, user_input],
+                          outputs=[chatbot, task_history, user_input]).then(
+            predict, [chatbot, task_history], [chatbot, task_history], show_progress=True
+        )
+        # 清除历史按钮的点击事件处理，重置聊天记录和任务历史
+        empty_bin.click(reset_state, outputs=[chatbot, task_history], show_progress=True)
+        # 重试按钮的点击事件处理，重新生成最后的响应
+        regen_btn.click(regenerate, [chatbot, task_history], [chatbot, task_history], show_progress=True)
+
+    # 启动Gradio界面
+    demo.queue().launch(
+        share=False,  # 不共享URL
+        inbrowser=args.inbrowser,  # 是否自动在浏览器中打开
+        server_port=args.server_port,  # 指定服务器端口
+        server_name=args.server_name,  # 指定服务器名称
+        ssl_certfile="/root/project/cert.pem", 
+        ssl_keyfile="/root/project/key.pem", 
+        ssl_verify=False
+    )
+
+if __name__ == "__main__":
+    args = _get_args()  # 获取命令行参数
+    if args.cpu_only:
+        device_map = "cpu"  # 如果指定了仅使用CPU，设置设备映射为CPU
+    else:
+        device_map = "auto"  # 否则自动选择设备
+
+    # 加载模型
+    model = Qwen2AudioForConditionalGeneration.from_pretrained(
+        args.checkpoint_path,
+        torch_dtype="auto",  # 自动选择数据类型
+        device_map=device_map,  # 设置设备映射
+        resume_download=True,  # 断点续传
+    ).eval()
+    model.generation_config.max_new_tokens = 2048  # 设置最大生成token数，用于长对话
+    print("generation_config", model.generation_config)
+    processor = AutoProcessor.from_pretrained(args.checkpoint_path, resume_download=True)  # 加载处理器
+    _launch_demo(args)  # 启动演示界面
+

text_clasi.py

@@ -0,0 +1,42 @@
+import platform
+import json
+import sys
+import os
+path_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))
+sys.path.append(os.path.join(path_root, "pytorch_textclassification"))
+print(path_root)
+# 分类下的引入, pytorch_textclassification
+from tcTools import get_current_time
+from tcRun import TextClassification
+from tcConfig import model_config
+
+evaluate_steps = 320  # 评估步数
+save_steps = 320  # 存储步数
+# pytorch预训练模型目录, 必填
+pretrained_model_name_or_path = "bert-base-chinese"
+# 训练-验证语料地址, 可以只输入训练地址
+path_corpus = os.path.join(path_root, "corpus", "text_classification", "school")
+path_train = os.path.join(path_corpus, "train.json")
+path_dev = os.path.join(path_corpus, "dev.json")
+
+
+if __name__ == "__main__":
+
+    model_config["evaluate_steps"] = evaluate_steps  # 评估步数
+    model_config["save_steps"] = save_steps  # 存储步数
+    model_config["path_train"] = path_train  # 训练模语料, 必须
+    model_config["path_dev"] = path_dev      # 验证语料, 可为None
+    model_config["path_tet"] = None          # 测试语料, 可为None
+    # 损失函数类型,
+    # multi-class:  可选 None(BCE), BCE, BCE_LOGITS, MSE, FOCAL_LOSS, DICE_LOSS, LABEL_SMOOTH
+    # multi-label:  SOFT_MARGIN_LOSS, PRIOR_MARGIN_LOSS, FOCAL_LOSS, CIRCLE_LOSS, DICE_LOSS等
+    model_config["path_tet"] = "FOCAL_LOSS"
+    os.environ["CUDA_VISIBLE_DEVICES"] = str(model_config["CUDA_VISIBLE_DEVICES"])
+
+    model_config["pretrained_model_name_or_path"] = pretrained_model_name_or_path
+    model_config["model_save_path"] = "../output/text_classification/model_{}".format(model_type[idx])
+    model_config["model_type"] = "BERT"
+    # main
+    lc = TextClassification(model_config)
+    lc.process()
+    lc.train()

web_demo_audio.py

@@ -0,0 +1,164 @@
+import gradio as gr
+import modelscope_studio as mgr
+import librosa
+from transformers import AutoProcessor, Qwen2AudioForConditionalGeneration
+from argparse import ArgumentParser
+
+DEFAULT_CKPT_PATH = 'Qwen/Qwen2-Audio-7B-Instruct'
+
+
+def _get_args():
+    parser = ArgumentParser()
+    parser.add_argument("-c", "--checkpoint-path", type=str, default=DEFAULT_CKPT_PATH,
+                        help="Checkpoint name or path, default to %(default)r")
+    parser.add_argument("--cpu-only", action="store_true", help="Run demo with CPU only")
+    parser.add_argument("--inbrowser", action="store_true", default=False,
+                        help="Automatically launch the interface in a new tab on the default browser.")
+    parser.add_argument("--server-port", type=int, default=8000,
+                        help="Demo server port.")
+    parser.add_argument("--server-name", type=str, default="127.0.0.1",
+                        help="Demo server name.")
+
+    args = parser.parse_args()
+    return args
+
+
+def add_text(chatbot, task_history, input):
+    text_content = input.text
+    content = []
+    if len(input.files) > 0:
+        for i in input.files:
+            content.append({'type': 'audio', 'audio_url': i.path})
+    if text_content:
+        content.append({'type': 'text', 'text': text_content})
+    task_history.append({"role": "user", "content": content})
+
+    chatbot.append([{
+        "text": input.text,
+        "files": input.files,
+    }, None])
+    return chatbot, task_history, None
+
+
+def add_file(chatbot, task_history, audio_file):
+    """Add audio file to the chat history."""
+    task_history.append({"role": "user", "content": [{"audio": audio_file.name}]})
+    chatbot.append((f"[Audio file: {audio_file.name}]", None))
+    return chatbot, task_history
+
+
+def reset_user_input():
+    """Reset the user input field."""
+    return gr.Textbox.update(value='')
+
+
+def reset_state(task_history):
+    """Reset the chat history."""
+    return [], []
+
+
+def regenerate(chatbot, task_history):
+    """Regenerate the last bot response."""
+    if task_history and task_history[-1]['role'] == 'assistant':
+        task_history.pop()
+        chatbot.pop()
+    if task_history:
+        chatbot, task_history = predict(chatbot, task_history)
+    return chatbot, task_history
+
+
+def predict(chatbot, task_history):
+    """Generate a response from the model."""
+    print(f"{task_history=}")
+    print(f"{chatbot=}")
+    text = processor.apply_chat_template(task_history, add_generation_prompt=True, tokenize=False)
+    audios = []
+    for message in task_history:
+        if isinstance(message["content"], list):
+            for ele in message["content"]:
+                if ele["type"] == "audio":
+                    audios.append(
+                        librosa.load(ele['audio_url'], sr=processor.feature_extractor.sampling_rate)[0]
+                    )
+
+    if len(audios)==0:
+        audios=None
+    print(f"{text=}")
+    print(f"{audios=}")
+    inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
+    if not _get_args().cpu_only:
+        inputs["input_ids"] = inputs.input_ids.to("cuda")
+
+    generate_ids = model.generate(**inputs, max_length=256)
+    generate_ids = generate_ids[:, inputs.input_ids.size(1):]
+
+    response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+    print(f"{response=}")
+    task_history.append({'role': 'assistant',
+                         'content': response})
+    chatbot.append((None, response))  # Add the response to chatbot
+    return chatbot, task_history
+
+
+def _launch_demo(args):
+    with gr.Blocks() as demo:
+        gr.Markdown(
+            """<p align="center"><img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/assets/blog/qwenaudio/qwen2audio_logo.png" style="height: 80px"/><p>""")
+        gr.Markdown("""<center><font size=8>Qwen2-Audio-Instruct Bot</center>""")
+        gr.Markdown(
+            """\
+    <center><font size=3>This WebUI is based on Qwen2-Audio-Instruct, developed by Alibaba Cloud. \
+    (本WebUI基于Qwen2-Audio-Instruct打造，实现聊天机器人功能。)</center>""")
+        gr.Markdown("""\
+    <center><font size=4>Qwen2-Audio <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B">🤖 </a> 
+    | <a href="https://huggingface.co/Qwen/Qwen2-Audio-7B">🤗</a>&nbsp ｜ 
+    Qwen2-Audio-Instruct <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B-Instruct">🤖 </a> | 
+    <a href="https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct">🤗</a>&nbsp ｜ 
+    &nbsp<a href="https://github.com/QwenLM/Qwen2-Audio">Github</a></center>""")
+        chatbot = mgr.Chatbot(label='Qwen2-Audio-7B-Instruct', elem_classes="control-height", height=750)
+
+        user_input = mgr.MultimodalInput(
+            interactive=True,
+            sources=['microphone', 'upload'],
+            submit_button_props=dict(value="🚀 Submit (发送)"),
+            upload_button_props=dict(value="📁 Upload (上传文件)", show_progress=True),
+        )
+        task_history = gr.State([])
+
+        with gr.Row():
+            empty_bin = gr.Button("🧹 Clear History (清除历史)")
+            regen_btn = gr.Button("🤔️ Regenerate (重试)")
+
+        user_input.submit(fn=add_text,
+                          inputs=[chatbot, task_history, user_input],
+                          outputs=[chatbot, task_history, user_input]).then(
+            predict, [chatbot, task_history], [chatbot, task_history], show_progress=True
+        )
+        empty_bin.click(reset_state, outputs=[chatbot, task_history], show_progress=True)
+        regen_btn.click(regenerate, [chatbot, task_history], [chatbot, task_history], show_progress=True)
+
+    demo.queue().launch(
+        share=True,
+        inbrowser=args.inbrowser,
+        server_port=args.server_port,
+        server_name=args.server_name,
+    )
+
+
+if __name__ == "__main__":
+    args = _get_args()
+    if args.cpu_only:
+        device_map = "cpu"
+    else:
+        device_map = "auto"
+
+    model = Qwen2AudioForConditionalGeneration.from_pretrained(
+        args.checkpoint_path,
+        torch_dtype="auto",
+        device_map=device_map,
+        resume_download=True,
+    ).eval()
+    model.generation_config.max_new_tokens = 2048  # For chat.
+    print("generation_config", model.generation_config)
+    processor = AutoProcessor.from_pretrained(args.checkpoint_path, resume_download=True)
+    _launch_demo(args)