File size: 13,672 Bytes
41ceddd
33d62f7
83dc4c8
541c07d
c55c219
958907e
41ceddd
b700c02
 
c55c219
 
 
 
 
 
 
41ceddd
c55c219
 
 
 
 
 
 
 
b700c02
 
 
 
 
 
 
39711bd
b700c02
 
 
 
 
 
 
 
 
 
 
39711bd
4e9d8a1
541c07d
56c7c7f
bdab1da
858c11b
 
 
 
 
 
 
 
 
4eab478
4b70abe
c2362ff
4b70abe
 
 
 
c2362ff
 
 
 
 
4b70abe
 
c2362ff
 
4b70abe
c2362ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4b70abe
 
 
 
 
 
c2362ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4b70abe
 
 
 
 
 
 
 
c2362ff
 
4eab478
858c11b
 
 
 
 
 
 
 
 
 
 
 
8f019f2
c2362ff
858c11b
 
 
 
 
 
 
4b70abe
27e435d
4b70abe
 
 
 
 
 
 
 
 
858c11b
 
 
ad1773e
c55c219
4e9d8a1
76479a0
6925286
44cd598
c55c219
b700c02
 
 
858c11b
c2362ff
56c7c7f
f45148f
 
 
 
 
 
 
4e9d8a1
858c11b
4b70abe
91dd1a0
4b70abe
 
 
 
 
b700c02
4b70abe
 
858c11b
 
993e22c
858c11b
993e22c
 
 
858c11b
 
4b70abe
b700c02
 
 
 
 
4b70abe
 
b700c02
56c7c7f
4b70abe
 
c1cbddf
 
 
 
 
 
 
 
541c07d
 
4b70abe
541c07d
 
 
 
4b70abe
db19271
4b70abe
79681cd
83dc4c8
4b70abe
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
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
import gradio as gr
import numpy as np
from audioldm import text_to_audio, build_model
from share_btn import community_icon_html, loading_icon_html, share_js

model_id="haoheliu/AudioLDM-S-Full"

audioldm = None
current_model_name = None

# def predict(input, history=[]):
#     # tokenize the new input sentence
#     new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')

#     # append the new user input tokens to the chat history
#     bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)

#     # generate a response 
#     history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()

#     # convert the tokens to text, and then split the responses into lines
#     response = tokenizer.decode(history[0]).split("<|endoftext|>")
#     response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list
#     return response, history
  
def text2audio(text, duration, guidance_scale, random_seed, n_candidates, model_name):
    global audioldm, current_model_name
    
    if audioldm is None or model_name != current_model_name:
        audioldm=build_model(model_name=model_name)
        current_model_name = model_name
        
    # print(text, length, guidance_scale)
    waveform = text_to_audio(
        latent_diffusion=audioldm,
        text=text,
        seed=random_seed,
        duration=duration,
        guidance_scale=guidance_scale,
        n_candidate_gen_per_text=int(n_candidates),
    )  # [bs, 1, samples]
    waveform = [
        gr.make_waveform((16000, wave[0]), bg_image="bg.png") for wave in waveform
    ]
    # waveform = [(16000, np.random.randn(16000)), (16000, np.random.randn(16000))]
    if(len(waveform) == 1):
      waveform = waveform[0]
    return waveform

# iface = gr.Interface(fn=text2audio, inputs=[
#         gr.Textbox(value="A man is speaking in a huge room", max_lines=1),
#         gr.Slider(2.5, 10, value=5, step=2.5),
#         gr.Slider(0, 5, value=2.5, step=0.5),
#         gr.Number(value=42)
#     ], outputs=[gr.Audio(label="Output", type="numpy"), gr.Audio(label="Output", type="numpy")],
#                 allow_flagging="never"
#                      )
# iface.launch(share=True)


css = """
        a {
            color: inherit;
            text-decoration: underline;
        }
        .gradio-container {
            font-family: 'IBM Plex Sans', sans-serif;
        }
        .gr-button {
            color: white;
            border-color: #000000;
            background: #000000;
        }
        input[type='range'] {
            accent-color: #000000;
        }
        .dark input[type='range'] {
            accent-color: #dfdfdf;
        }
        .container {
            max-width: 730px;
            margin: auto;
            padding-top: 1.5rem;
        }
        #gallery {
            min-height: 22rem;
            margin-bottom: 15px;
            margin-left: auto;
            margin-right: auto;
            border-bottom-right-radius: .5rem !important;
            border-bottom-left-radius: .5rem !important;
        }
        #gallery>div>.h-full {
            min-height: 20rem;
        }
        .details:hover {
            text-decoration: underline;
        }
        .gr-button {
            white-space: nowrap;
        }
        .gr-button:focus {
            border-color: rgb(147 197 253 / var(--tw-border-opacity));
            outline: none;
            box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
            --tw-border-opacity: 1;
            --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
            --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
            --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
            --tw-ring-opacity: .5;
        }
        #advanced-btn {
            font-size: .7rem !important;
            line-height: 19px;
            margin-top: 12px;
            margin-bottom: 12px;
            padding: 2px 8px;
            border-radius: 14px !important;
        }
        #advanced-options {
            margin-bottom: 20px;
        }
        .footer {
            margin-bottom: 45px;
            margin-top: 35px;
            text-align: center;
            border-bottom: 1px solid #e5e5e5;
        }
        .footer>p {
            font-size: .8rem;
            display: inline-block;
            padding: 0 10px;
            transform: translateY(10px);
            background: white;
        }
        .dark .footer {
            border-color: #303030;
        }
        .dark .footer>p {
            background: #0b0f19;
        }
        .acknowledgments h4{
            margin: 1.25em 0 .25em 0;
            font-weight: bold;
            font-size: 115%;
        }
        #container-advanced-btns{
            display: flex;
            flex-wrap: wrap;
            justify-content: space-between;
            align-items: center;
        }
        .animate-spin {
            animation: spin 1s linear infinite;
        }
        @keyframes spin {
            from {
                transform: rotate(0deg);
            }
            to {
                transform: rotate(360deg);
            }
        }
        #share-btn-container {
            display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
            margin-top: 10px;
            margin-left: auto;
        }
        #share-btn {
            all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;right:0;
        }
        #share-btn * {
            all: unset;
        }
        #share-btn-container div:nth-child(-n+2){
            width: auto !important;
            min-height: 0px !important;
        }
        #share-btn-container .wrap {
            display: none !important;
        }
        .gr-form{
            flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
        }
        #prompt-container{
            gap: 0;
        }
        #generated_id{
            min-height: 700px
        }
        #setting_id{
          margin-bottom: 12px;
          text-align: center;
          font-weight: 900;
        }
"""
iface = gr.Blocks(css=css)

with iface:
    gr.HTML(
        """
            <div style="text-align: center; max-width: 700px; margin: 0 auto;">
              <div
                style="
                  display: inline-flex;
                  align-items: center;
                  gap: 0.8rem;
                  font-size: 1.75rem;
                "
              >
                <h1 style="font-weight: 900; margin-bottom: 7px; line-height: normal;">
                  AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
                </h1>
              </div>
              <p style="margin-bottom: 10px; font-size: 94%">
                <a href="https://arxiv.org/abs/2301.12503">[Paper]</a>  <a href="https://audioldm.github.io/">[Project page]</a>
              </p>
            </div>
        """
    )
    gr.HTML("""
        <h1 style="font-weight: 900; margin-bottom: 7px;">
        AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
        </h1>
        <p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings.
        <br/>
        <a href="https://huggingface.co/spaces/haoheliu/audioldm-text-to-audio-generation?duplicate=true">
        <img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
        <p/>
    """)
    with gr.Group():
        with gr.Box():
            ############# Input
            textbox = gr.Textbox(value="A hammer is hitting a wooden surface", max_lines=1, label="Input your text here. Your text is important for the audio quality. Please ensure it is descriptive by using more adjectives.", elem_id="prompt-in")

            with gr.Accordion("Click to modify detailed configurations", open=False):
              seed = gr.Number(value=45, label="Change this value (any integer number) will lead to a different generation result.")
              duration = gr.Slider(2.5, 10, value=10, step=2.5, label="Duration (seconds)")
              guidance_scale = gr.Slider(0, 4, value=2.5, step=0.5, label="Guidance scale (Large => better quality and relavancy to text; Small => better diversity)")
              n_candidates = gr.Slider(1, 5, value=3, step=1, label="Automatic quality control. This number control the number of candidates (e.g., generate three audios and choose the best to show you). A Larger value usually lead to better quality with heavier computation")
              model_name = gr.Dropdown(
                    ["audioldm-m-text-ft", "audioldm-s-text-ft", "audioldm-m-full","audioldm-s-full-v2", "audioldm-s-full", "audioldm-l-full"], value="audioldm-m-text-ft", label="Choose the model to use. audioldm-m-text-ft and audioldm-s-text-ft are recommanded. -s- means small, -m- means medium and -l- means large",
                )
            ############# Output
            # outputs=gr.Audio(label="Output", type="numpy")
            outputs=gr.Video(label="Output", elem_id="output-video")
            
            # with gr.Group(elem_id="container-advanced-btns"):
            #   # advanced_button = gr.Button("Advanced options", elem_id="advanced-btn")
            #   with gr.Group(elem_id="share-btn-container"):
            #     community_icon = gr.HTML(community_icon_html, visible=False)
            #     loading_icon = gr.HTML(loading_icon_html, visible=False)
            #     share_button = gr.Button("Share to community", elem_id="share-btn", visible=False)
            # outputs=[gr.Audio(label="Output", type="numpy"), gr.Audio(label="Output", type="numpy")]
            btn = gr.Button("Submit").style(full_width=True)

        with gr.Group(elem_id="share-btn-container", visible=False):
            community_icon = gr.HTML(community_icon_html)
            loading_icon = gr.HTML(loading_icon_html)
            share_button = gr.Button("Share to community", elem_id="share-btn")

        btn.click(text2audio, inputs=[
                  textbox, duration, guidance_scale, seed, n_candidates, model_name], outputs=[outputs])

        share_button.click(None, [], [], _js=share_js)
        gr.HTML('''
        <div class="footer" style="text-align: center; max-width: 700px; margin: 0 auto;">
                    <p>Follow the latest update of AudioLDM on our<a href="https://github.com/haoheliu/AudioLDM" style="text-decoration: underline;" target="_blank"> Github repo</a>
                    </p>
                    <br>
                    <p>Model by <a href="https://twitter.com/LiuHaohe" style="text-decoration: underline;" target="_blank">Haohe Liu</a></p>
                    <br>
        </div>
        ''')
        gr.Examples([
            ["A hammer is hitting a wooden surface", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
            ["Peaceful and calming ambient music with singing bowl and other instruments.", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
            ["A man is speaking in a small room.", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
            ["A female is speaking followed by footstep sound", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
            ["Wooden table tapping sound followed by water pouring sound.", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
        ],
            fn=text2audio,
            inputs=[textbox, duration, guidance_scale, seed, n_candidates, model_name],
            outputs=[outputs],
            cache_examples=True,
        )
        gr.HTML('''
                <div class="acknowledgements">
                <p>Essential Tricks for Enhancing the Quality of Your Generated Audio</p>
                <p>1. Try to use more adjectives to describe your sound. For example: "A man is speaking clearly and slowly in a large room" is better than "A man is speaking". This can make sure AudioLDM understands what you want.</p>
                <p>2. Try to use different random seeds, which can affect the generation quality significantly sometimes.</p>
                <p>3. It's better to use general terms like 'man' or 'woman' instead of specific names for individuals or abstract objects that humans may not be familiar with, such as 'mummy'.</p>
                </div>
                ''')
        with gr.Accordion("Additional information", open=False):
            gr.HTML(
                """
                <div class="acknowledgments">
                    <p> We build the model with data from <a href="http://research.google.com/audioset/">AudioSet</a>, <a href="https://freesound.org/">Freesound</a> and <a href="https://sound-effects.bbcrewind.co.uk/">BBC Sound Effect library</a>. We share this demo based on the <a href="https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/375954/Research.pdf">UK copyright exception</a> of data for academic research. </p>
                            </div>
                        """
            )
# <p>This demo is strictly for research demo purpose only. For commercial use please <a href="haoheliu@gmail.com">contact us</a>.</p>

iface.queue(concurrency_count=2)
iface.launch(debug=True)
# iface.launch(debug=True, share=True)