[大模型]Qwen-Audio-chat WebDemo 部署_ollama qwen-audio-chat

Qwen-Audio-chat WebDemo 部署

Qwen-Audio 介绍

Qwen-Audio 是阿里云研发的大规模音频语言模型（Large Audio Language Model）。Qwen-Audio 可以以多种音频 (包括说话人语音、自然音、音乐、歌声）和文本作为输入，并以文本作为输出。

环境准备

在autodl平台中租一个3090等24G显存的显卡机器，如下图所示镜像选择PyTorch–>2.0.0–>3.8(ubuntu20.04)–>11.8（11.3版本以上的都可以）
接下来打开刚刚租用服务器的JupyterLab图像， 并且打开其中的终端开始环境配置、模型下载和运行演示。

pip换源和安装依赖包

# 升级pip
python -m pip install --upgrade pip
# 更换 pypi 源加速库的安装
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple

pip install modelscope==1.9.5

pip install accelerate
pip install tiktoken
pip install einops
pip install transformers_stream_generator==0.0.4
pip install scipy
pip install torchvision
pip install pillow
pip install tensorboard
pip install matplotlib
pip install transformers==4.32.0
pip install gradio==3.39.0
pip install nest_asyncio
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

模型下载

使用 modelscope 中的snapshot_download函数下载模型，第一个参数为模型名称，参数cache_dir为模型的下载路径。

在 /root/autodl-tmp 路径下新建 download.py 文件并在其中输入以下内容，粘贴代码后记得保存文件，如下图所示。并运行 python /root/autodl-tmp/download.py 执行下载，模型大小为 20 GB，下载模型大概需要10~20分钟

import torch
from modelscope import snapshot_download, AutoModel, AutoTokenizer
from modelscope import GenerationConfig
model_dir = snapshot_download('qwen/Qwen-Audio-Chat', cache_dir='/root/autodl-tmp', revision='master')
1
2
3
4

代码准备

在/root/autodl-tmp路径下新建 chatBot.py 文件并在其中输入以下内容，粘贴代码后记得保存文件。下面的代码有很详细的注释，大家如有不理解的地方，欢迎提出issue。

# Copyright (c) Alibaba Cloud.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

"""A simple web interactive chat demo based on gradio."""

from argparse import ArgumentParser
from pathlib import Path

import copy
import gradio as gr
import os
import re
import secrets
import tempfile
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
from pydub import AudioSegment

# DEFAULT_CKPT_PATH = 'Qwen/Qwen-Audio-Chat'
DEFAULT_CKPT_PATH = "/root/autodl-tmp/qwen/Qwen-Audio-Chat"


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("--share", action="store_true", default=False,
                        help="Create a publicly shareable link for the interface.")
    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 _load_model_tokenizer(args):
    tokenizer = AutoTokenizer.from_pretrained(
        args.checkpoint_path, trust_remote_code=True, resume_download=True,
    )

    if args.cpu_only:
        device_map = "cpu"
    else:
        device_map = "cuda"

    model = AutoModelForCausalLM.from_pretrained(
        args.checkpoint_path,
        device_map=device_map,
        trust_remote_code=True,
        resume_download=True,
    ).eval()
    model.generation_config = GenerationConfig.from_pretrained(
        args.checkpoint_path, trust_remote_code=True, resume_download=True,
    )

    return model, tokenizer


def _parse_text(text):
    lines = text.split("\n")
    lines = [line for line in lines if line != ""]
    count = 0
    for i, line in enumerate(lines):
        if "```" in line:
            count += 1
            items = line.split("`")
            if count % 2 == 1:
                lines[i] = f'<pre><code class="language-{items[-1]}">'
            else:
                lines[i] = f"<br></code></pre>"
        else:
            if i > 0:
                if count % 2 == 1:
                    line = line.replace("`", r"\`")
                    line = line.replace("<", "&lt;")
                    line = line.replace(">", "&gt;")
                    line = line.replace(" ", "&nbsp;")
                    line = line.replace("*", "&ast;")
                    line = line.replace("_", "&lowbar;")
                    line = line.replace("-", "&#45;")
                    line = line.replace(".", "&#46;")
                    line = line.replace("!", "&#33;")
                    line = line.replace("(", "&#40;")
                    line = line.replace(")", "&#41;")
                    line = line.replace("$", "&#36;")
                lines[i] = "<br>" + line
    text = "".join(lines)
    return text


def _launch_demo(args, model, tokenizer):
    uploaded_file_dir = os.environ.get("GRADIO_TEMP_DIR") or str(
        Path(tempfile.gettempdir()) / "gradio"
    )

    def predict(_chatbot, task_history):
        query = task_history[-1][0]
        print("User: " + _parse_text(query))
        history_cp = copy.deepcopy(task_history)
        full_response = ""

        history_filter = []
        audio_idx = 1
        pre = ""
        global last_audio
        for i, (q, a) in enumerate(history_cp):
            if isinstance(q, (tuple, list)):
                last_audio = q[0]
                q = f'Audio {audio_idx}: <audio>{q[0]}</audio>'
                pre += q + '\n'
                audio_idx += 1
            else:
                pre += q
                history_filter.append((pre, a))
                pre = ""
        history, message = history_filter[:-1], history_filter[-1][0]
        response, history = model.chat(tokenizer, message, history=history)
        ts_pattern = r"<\|\d{1,2}\.\d+\|>"
        all_time_stamps = re.findall(ts_pattern, response)
        print(response)
        if (len(all_time_stamps) > 0) and (len(all_time_stamps) % 2 ==0) and last_audio:
            ts_float = [ float(t.replace("<|","").replace("|>","")) for t in all_time_stamps]
            ts_float_pair = [ts_float[i:i + 2] for i in range(0,len(all_time_stamps),2)]
            # 读取音频文件
            format = os.path.splitext(last_audio)[-1].replace(".","")
            audio_file = AudioSegment.from_file(last_audio, format=format)
            chat_response_t = response.replace("<|", "").replace("|>", "")
            chat_response = chat_response_t
            temp_dir = secrets.token_hex(20)
            temp_dir = Path(uploaded_file_dir) / temp_dir
            temp_dir.mkdir(exist_ok=True, parents=True)
            # 截取音频文件
            for pair in ts_float_pair:
                audio_clip = audio_file[pair[0] * 1000: pair[1] * 1000]
                # 保存音频文件
                name = f"tmp{secrets.token_hex(5)}.{format}"
                filename = temp_dir / name
                audio_clip.export(filename, format=format)
                _chatbot[-1] = (_parse_text(query), chat_response)
                _chatbot.append((None, (str(filename),)))
        else:
            _chatbot[-1] = (_parse_text(query), response)

        full_response = _parse_text(response)

        task_history[-1] = (query, full_response)
        print("Qwen-Audio-Chat: " + _parse_text(full_response))
        return _chatbot

    def regenerate(_chatbot, task_history):
        if not task_history:
            return _chatbot
        item = task_history[-1]
        if item[1] is None:
            return _chatbot
        task_history[-1] = (item[0], None)
        chatbot_item = _chatbot.pop(-1)
        if chatbot_item[0] is None:
            _chatbot[-1] = (_chatbot[-1][0], None)
        else:
            _chatbot.append((chatbot_item[0], None))
        return predict(_chatbot, task_history)

    def add_text(history, task_history, text):
        history = history + [(_parse_text(text), None)]
        task_history = task_history + [(text, None)]
        return history, task_history, ""

    def add_file(history, task_history, file):
        history = history + [((file.name,), None)]
        task_history = task_history + [((file.name,), None)]
        return history, task_history

    def add_mic(history, task_history, file):
        if file is None:
            return history, task_history
        os.rename(file, file + '.wav')
        print("add_mic file:", file)
        print("add_mic history:", history)
        print("add_mic task_history:", task_history)
        # history = history + [((file.name,), None)]
        # task_history = task_history + [((file.name,), None)]
        task_history = task_history + [((file + '.wav',), None)]
        history = history + [((file + '.wav',), None)]
        print("task_history", task_history)
        return history, task_history

    def reset_user_input():
        return gr.update(value="")

    def reset_state(task_history):
        task_history.clear()
        return []

    with gr.Blocks() as demo:
        gr.Markdown("""\
<p align="center"><img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/logo.jpg" style="height: 80px"/><p>""")  ## todo
        gr.Markdown("""<center><font size=8>Qwen-Audio-Chat Bot</center>""")
        gr.Markdown(
            """\
<center><font size=3>This WebUI is based on Qwen-Audio-Chat, developed by Alibaba Cloud. \
(本WebUI基于Qwen-Audio-Chat打造，实现聊天机器人功能。)</center>""")
        gr.Markdown("""\
<center><font size=4>Qwen-Audio <a href="https://modelscope.cn/models/qwen/Qwen-Audio/summary">
声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/码创造者/article/detail/795154