File size: 10,449 Bytes
7725096
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5971478
7725096
 
 
 
 
 
2ad4c73
7725096
 
 
 
 
 
 
 
 
 
 
bac8277
7725096
d101188
7725096
 
 
 
 
 
 
 
5971478
7725096
 
 
 
 
 
 
 
 
 
 
 
5971478
7725096
 
5971478
7725096
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d580aa
7725096
 
 
 
 
 
 
 
 
 
 
 
 
 
dcc9bdb
 
7725096
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ebf39b7
7725096
 
 
 
 
 
 
 
 
 
 
 
 
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
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
# 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 import GenerationConfig
# from modelscope.hub.api import HubApi
from pydub import AudioSegment
import os
YOUR_ACCESS_TOKEN = os.getenv('YOUR_ACCESS_TOKEN')

# api = HubApi()
# api.login(YOUR_ACCESS_TOKEN)


# DEFAULT_CKPT_PATH = snapshot_download('qwen/Qwen-Audio-Chat')
DEFAULT_CKPT_PATH = "xun/Qwen-Audio-Chat-Int4"

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=7860,
                        help="Demo server port.")
    parser.add_argument("--server-name", type=str, default="0.0.0.0",
                        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, token=YOUR_ACCESS_TOKEN
    )

    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,
        token=YOUR_ACCESS_TOKEN
    ).eval()
    model.generation_config = GenerationConfig.from_pretrained(
        args.checkpoint_path, trust_remote_code=True, resume_download=True, token=YOUR_ACCESS_TOKEN
    )

    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)]
            # θ―»ε–ιŸ³ι’‘ζ–‡δ»Ά
            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)
            # ζˆͺε–ιŸ³ι’‘ζ–‡δ»Ά
            for pair in ts_float_pair:
                audio_clip = audio_file[pair[0] * 1000: pair[1] * 1000]
                # δΏε­˜ιŸ³ι’‘ζ–‡δ»Ά
                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/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. </center>""")
        gr.Markdown("""\
<center><font size=4>Qwen-Audio <a href="https://modelscope.cn/models/qwen/Qwen-Audio/summary">πŸ€– </a> 
| <a href="https://huggingface.co/Qwen/Qwen-Audio">πŸ€—</a>&nbsp | 
Qwen-Audio-Chat <a href="https://modelscope.cn/models/qwen/Qwen-Audio-Chat/summary">πŸ€– </a> | 
<a href="https://huggingface.co/Qwen/Qwen-Audio-Chat">πŸ€—</a>&nbsp | 
&nbsp<a href="https://github.com/QwenLM/Qwen-Audio">Github</a></center>""")

        chatbot = gr.Chatbot(label='Qwen-Audio-Chat', elem_classes="control-height", height=750)
        query = gr.Textbox(lines=2, label='Input')
        task_history = gr.State([])
        # mic = gr.Audio(source="microphone", type="filepath")
        mic = gr.Audio(type="filepath")

        with gr.Row():
            empty_bin = gr.Button("🧹 Clear History")
            submit_btn = gr.Button("πŸš€ Submit")
            regen_btn = gr.Button("πŸ€”οΈ Regenerate")
            addfile_btn = gr.UploadButton("πŸ“ Upload", file_types=["audio"])

        mic.change(add_mic, [chatbot, task_history, mic], [chatbot, task_history])
        submit_btn.click(add_text, [chatbot, task_history, query], [chatbot, task_history]).then(
            predict, [chatbot, task_history], [chatbot], show_progress=True
        )
        submit_btn.click(reset_user_input, [], [query])
        empty_bin.click(reset_state, [task_history], [chatbot], show_progress=True)
        regen_btn.click(regenerate, [chatbot, task_history], [chatbot], show_progress=True)
        addfile_btn.upload(add_file, [chatbot, task_history, addfile_btn], [chatbot, task_history], show_progress=True)

        gr.Markdown("""\
<font size=2>Note: This demo is governed by the original license of Qwen-Audio. \
We strongly advise users not to knowingly generate or allow others to knowingly generate harmful content, \
including hate speech, violence, pornography, deception, etc. \
""")

    demo.queue().launch(
        share=args.share,
        inbrowser=args.inbrowser,
        server_port=args.server_port,
        server_name=args.server_name,
        # file_directories=["/tmp/"]
    )


def main():
    args = _get_args()

    model, tokenizer = _load_model_tokenizer(args)

    _launch_demo(args, model, tokenizer)


if __name__ == '__main__':
    main()